Search

Small moving objects at far distance always occupy only one or a few pixels in image and exhibit extremely limited visual features, which bring great challenges to motion detection. Highly evolved visual systems endow flying insects with remarkable ability to pursue tiny mates and prey, providing a good template to develop image processing method for small target motion detection. The insects’ excellent sensitivity to small moving objects is believed to come from a class of specific neurons called small target motion detectors (STMDs). However, existing STMD-based methods often experience performance degradation when coping with complex natural scenes. In this paper, we propose a bio-inspired visual system with spatio-temporal feedback mechanism (called Spatio-Temporal Feedback STMD) to suppress false positive background movement while enhancing system responses to small targets. Specifically, the proposed visual system is composed of two complementary subnetworks and a feedback loop. The first subnetwork is designed to extract spatial and temporal movement patterns of cluttered background by neuronal ensemble coding. The second subnetwork is developed to capture small target motion information where its output and signal from the first subnetwork are integrated together via the feedback loop to filter out background false positives in a recurrent manner. Experimental results demonstrate that the proposed spatio-temporal feedback visual system is more competitive than existing methods in discriminating small moving targets from complex natural environments. [ABSTRACT FROM AUTHOR]

Recently, distributed learning approaches have been studied for using data from multiple sources without sharing them, but they are not usually suitable in applications where each client carries out different tasks. Meanwhile, Transformer has been widely explored in computer vision area due to its capability to learn the common representation through global attention. By leveraging the advantages of Transformer, here we present a new distributed learning framework for multiple image processing tasks, allowing clients to learn distinct tasks with their local data. This arises from a disentangled representation of local and non-local features using a task-specific head/tail and a task-agnostic Vision Transformer. Each client learns a translation from its own task to a common representation using the task-specific networks, while the Transformer body on the server learns global attention between the features embedded in the representation. To enable decomposition between the task-specific and common representations, we propose an alternating training strategy between clients and server. Experimental results on distributed learning for various tasks show that our method synergistically improves the performance of each client with its own data. [ABSTRACT FROM AUTHOR]

Deep generative models have proven to be effective priors for solving a variety of image processing problems. However, the learning of realistic image priors, based on a large number of parameters, requires a large amount of training data. It has been shown recently, with the so-called deep image prior (DIP), that randomly initialized neural networks can act as good image priors without learning. In this paper, we propose a deep generative model for light fields, which is compact and which does not require any training data other than the light field itself. To show the potential of the proposed generative model, we develop a complete light field compression scheme with quantization-aware learning and entropy coding of the quantized weights. Experimental results show that the proposed method yields very competitive results compared with state-of-the-art light field compression methods, both in terms of PSNR and MS-SSIM metrics. [ABSTRACT FROM AUTHOR]

Arbitrary style transfer aims at migrating the style of a reference style painting to a target content image. Existing methods find it challenging to achieve good content fidelity and style migration at the same time. Moreover, they all rely on manually defined content and style, which is of limited universality and robustness. In this paper, we propose to introduce contrastive learning into style transfer, instructing the network to automatically learn to model the structural content and artistic style based on natural contrastive relationships in style transfer. Compared with existing methods, our learned modeling of content and style is more robust and universal. In addition, we further propose instance-wise contrastive style losses and a patch-wise contrastive content loss to guide style transfer. Combining the proposed contrastive losses and two self-reconstruction strategies, we develop a new style transfer framework, which is pluggable and can be flexibly applied to various style transfer modules. Experimental results demonstrate that our method has strong flexibility and synthesizes stylized images with higher quality. [ABSTRACT FROM AUTHOR]

Adaptive Fourier decomposition (AFD) is a newly developed signal processing tool that can adaptively decompose any single signal using a Szegö kernel dictionary. To process multiple signals, a novel stochastic-AFD (SAFD) theory was recently proposed. The innovation of this study is twofold. First, a SAFD-based general multi-signal sparse representation learning algorithm is designed and implemented for the first time in the literature, which can be used in many signal and image processing areas. Second, a novel SAFD based image compression framework is proposed. The algorithm design and implementation of the SAFD theory and image compression methods are presented in detail. The proposed compression methods are compared with 13 other state-of-the-art compression methods, including JPEG, JPEG2000, BPG, and other popular deep learning-based methods. The experimental results show that our methods achieve the best balanced performance. The proposed methods are based on single image adaptive sparse representation learning, and they require no pre-training. In addition, the decompression quality or compression efficiency can be easily adjusted by a single parameter, that is, the decomposition level. Our method is supported by a solid mathematical foundation, which has the potential to become a new core technology in image compression. [ABSTRACT FROM AUTHOR]

Serving as an essential step for many applications of image processing, superpixel generation has attracted a lot of attentions. Most existing superpixel generation algorithms focus on the boundary adherence and compactness of the superpixels, but ignore the topological consistency between the superpixels, which severely limites their applications in the subsequent tasks, especially in the CNN based image processing tasks. In this paper, we present a fast lattice superpixel generation algorithm, which can generate superpixels with lattice topology like the original pixels. We also propose a local similarity loss function to improve the segmentation accuracy of the generated lattice superpixels. The whole algorithm is parallelly implemented on GPU. We perform extensive experiments on three datasets (i.e., BSDS500, NYUv2 and VOC) to verify the efficacy of our algorithm. The experimental results show that our method achieves competitive results compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Compressive covariance estimation has arisen as a class of techniques whose aim is to obtain second-order statistics of stochastic processes from compressive measurements. Recently, these methods have been used in various image processing and communications applications, including denoising, spectrum sensing, and compression. Notice that estimating the covariance matrix from compressive samples leads to ill-posed minimizations with severe performance loss at high compression rates. In this regard, a regularization term is typically aggregated to the cost function to consider prior information about a particular property of the covariance matrix. Hence, this paper proposes an algorithm based on the projected gradient method to recover low-rank or Toeplitz approximations of the covariance matrix from compressive measurements. The proposed algorithm divides the compressive measurements into data subsets projected onto different subspaces and accurately estimates the covariance matrix by solving a single optimization problem assuming that each data subset contains an approximation of the signal statistics. Furthermore, gradient filtering is included at every iteration of the proposed algorithm to minimize the estimation error. The error induced by the proposed splitting approach is analytically derived along with the convergence guarantees of the proposed method. The proposed algorithm estimates the covariance matrix of hyperspectral images from synthetic and real compressive samples. Extensive simulations show that the proposed algorithm can effectively recover the covariance matrix of hyperspectral images from compressive measurements with high compression ratios ($8-15\%$ approx) in noisy scenarios. Moreover, simulations and theoretical results show that the filtering step reduces the recovery error up to twice the number of eigenvectors. Finally, an optical implementation is proposed, and real measurements are used to validate the theoretical findings. [ABSTRACT FROM AUTHOR]

We present data structures and algorithms for native implementations of discrete convolution operators over Adaptive Particle Representations (APR) of images on parallel computer architectures. The APR is a content-adaptive image representation that locally adapts the sampling resolution to the image signal. It has been developed as an alternative to pixel representations for large, sparse images as they typically occur in fluorescence microscopy. It has been shown to reduce the memory and runtime costs of storing, visualizing, and processing such images. This, however, requires that image processing natively operates on APRs, without intermediately reverting to pixels. Designing efficient and scalable APR-native image processing primitives, however, is complicated by the APR’s irregular memory structure. Here, we provide the algorithmic building blocks required to efficiently and natively process APR images using a wide range of algorithms that can be formulated in terms of discrete convolutions. We show that APR convolution naturally leads to scale-adaptive algorithms that efficiently parallelize on multi-core CPU and GPU architectures. We quantify the speedups in comparison to pixel-based algorithms and convolutions on evenly sampled data. We achieve pixel-equivalent throughputs of up to 1TB/s on a single Nvidia GeForce RTX 2080 gaming GPU, requiring up to two orders of magnitude less memory than a pixel-based implementation. [ABSTRACT FROM AUTHOR]

Given a photo of a subject, ability to generate a caricature image that captures distinct characteristics of the subject but with certain exaggeration of their prominent features is of fundamental importance to image processing and facial recognition. There are two main challenges in this task: shape exaggeration and style transfer. The former morphs and exaggerates key facial features of the subject, while the latter generates caricature images in a certain artistic style. In this paper, we propose a CAricature Style Transfer (CAST) framework for caricature generation. There are two modules in the proposed framework. The first is a geometric warping module. Different from the existing style transfer methods, we incorporate the Whitening and Coloring Transformation (WCT) in the geometric style transfer. The WCT is learned on photo and caricature landmarks or the caricature landmark space of a specific artist and is capable of transforming input photo landmarks to caricature landmarks. The second module is a texture style rendering module. We propose a new style transfer method by considering a semantic region-aligned style transfer via affinity constraint. Given a reference caricature image as the style reference, this module is capable of transferring styles between the same or similar semantic regions in caricatures and photos. Furthermore, it can transfer visual attributes of the reference caricatures (such as mouth shape and expressions) to the output caricatures. Experiments have shown desirable effects of the proposed method in transferring both the geometric and artistic texture styles of caricatures. Both qualitative and quantitative results show that the CAST framework is more effective compared than the state-of-the-art caricature generation methods. [ABSTRACT FROM AUTHOR]

Feature matching, which refers to identifying and then corresponding the same or similar visual pattern from two or more images, is a key technique in any image processing task that requires establishing good correspondences between images. Given potential correspondences (matches) in two scenes, a novel whole-part deep learning framework, termed as Context Structure Representation Network (CSR-Net), is designed to infer the probabilities of arbitrary correspondences being inliers. Traditional approaches commonly build the local relation between correspondences by manually engineered criteria. Different from existing attempts, the main idea of our work is to learn explicitly neighborhood structure of each correspondence, allowing us to formulate the matching problem into a dynamic local structure consensus evaluation in an end-to-end fashion. For this purpose, we propose a permutation-invariant STructure Representation (STR) learning module, which can easily merge different types of networks into a unified architecture to deal with sparse matches directly. By the collaborative use of STR, we introduce a Context-Aware Attention (CAA) mechanism to adaptively re-calibrate structure features via a rotation-invariant context aware encoding and simple feature gating, thus arising the ability of fine-grained patterns recognition. Moreover, to further weaken the cost of establishing reliable correspondences, the CSR-Net is formulated as whole-part consensus learning, where the aim of whole level is compensating rigid transformations. In order to demonstrate our CSR-Net can effectively boost the baselines, we intensively experiment on image matching and other visual tasks. The results of the experiment confirm that the matching performances of CSR-Net have significantly improved over nine state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

3D volumetric image processing has attracted increasing attention in the last decades, in which one major research area is to develop efficient lossless volumetric image compression techniques to better store and transmit such images with massive amount of information. In this work, we propose the first end-to-end optimized learning framework for losslessly compressing 3D volumetric data. Our approach builds upon a hierarchical compression scheme by additionally introducing the intra-slice auxiliary features and estimating the entropy model based on both intra-slice and inter-slice latent priors. Specifically, we first extract the hierarchical intra-slice auxiliary features through multi-scale feature extraction modules. Then, an Intra-slice and Inter-slice Conditional Entropy Coding module is proposed to fuse the intra-slice and inter-slice information from different scales as the context information. Based on such context information, we can predict the distributions for both intra-slice auxiliary features and the slice images. To further improve the lossless compression performance, we also introduce two new gating mechanisms called Intra-Gate and Inter-Gate to generate the optimal feature representations for better information fusion. Eventually, we can produce the bitstream for losslessly compressing volumetric images based on the estimated entropy model. Different from the existing lossless volumetric image codecs, our end-to-end optimized framework jointly learns both intra-slice auxiliary features at different scales for each slice and inter-slice latent features from previously encoded slices for better entropy estimation. The extensive experimental results indicate that our framework outperforms the state-of-the-art hand-crafted lossless volumetric image codecs (e.g., JP3D) and the learning-based lossless image compression method on four volumetric image benchmarks for losslessly compressing both 3D Medical Images and Hyper-Spectral Images. [ABSTRACT FROM AUTHOR]

In this paper, we make the first benchmark effort to elaborate on the superiority of using RAW images in the low light enhancement and develop a novel alternative route to utilize RAW images in a more flexible and practical way. Inspired by a full consideration on the typical image processing pipeline, we are inspired to develop a new evaluation framework, Factorized Enhancement Model (FEM), which decomposes the properties of RAW images into measurable factors and provides a tool for exploring how properties of RAW images affect the enhancement performance empirically. The empirical benchmark results show that the Linearity of data and Exposure Time recorded in meta-data play the most critical role, which brings distinct performance gains in various measures over the approaches taking the sRGB images as input. With the insights obtained from the benchmark results in mind, a RAW-guiding Exposure Enhancement Network (REENet) is developed, which makes trade-offs between the advantages and inaccessibility of RAW images in real applications in a way of using RAW images only in the training phase. REENet projects sRGB images into linear RAW domains to apply constraints with corresponding RAW images to reduce the difficulty of modeling training. After that, in the testing phase, our REENet does not rely on RAW images. Experimental results demonstrate not only the superiority of REENet to state-of-the-art sRGB-based methods and but also the effectiveness of the RAW guidance and all components. [ABSTRACT FROM AUTHOR]

Convolutional dictionary learning has become increasingly popular in signal and image processing for its ability to overcome the limitations of traditional patch-based dictionary learning. Although most studies on convolutional dictionary learning mainly focus on the unimodal case, real-world image processing tasks usually involve images from multiple modalities, e.g., visible and near-infrared (NIR) images. Thus, it is necessary to explore convolutional dictionary learning across different modalities. In this paper, we propose a novel multi-modal convolutional dictionary learning algorithm, which efficiently correlates different image modalities and fully considers neighborhood information at the image level. In this model, each modality is represented by two convolutional dictionaries, in which one dictionary is for common feature representation and the other is for unique feature representation. The model is constrained by the requirement that the convolutional sparse representations (CSRs) for the common features should be the same across different modalities, considering that these images are captured from the same scene. We propose a new training method based on the alternating direction method of multipliers (ADMM) to alternatively learn the common and unique dictionaries in the discrete Fourier transform (DFT) domain. We show that our model converges in less than 20 iterations between the convolutional dictionary updating and the CSRs calculation. The effectiveness of the proposed dictionary learning algorithm is demonstrated on various multimodal image processing tasks, achieves better performance than both dictionary learning methods and deep learning based methods with limited training data. [ABSTRACT FROM AUTHOR]

Constructing effective priors is critical to solving ill-posed inverse problems in image processing and computational imaging. Recent works focused on exploiting non-local similarity by grouping similar patches for image modeling, and demonstrated state-of-the-art results in many image restoration applications. However, compared to classic methods based on filtering or sparsity, non-local algorithms are more time-consuming, mainly due to the highly inefficient block matching step, i.e., distance between every pair of overlapping patches needs to be computed. In this work, we propose a novel Self-Convolution operator to exploit image non-local properties in a unified framework. We prove that the proposed Self-Convolution based formulation can generalize the commonly-used non-local modeling methods, as well as produce results equivalent to standard methods, but with much cheaper computation. Furthermore, by applying Self-Convolution, we propose an effective multi-modality image restoration scheme, which is much more efficient than conventional block matching for non-local modeling. Experimental results demonstrate that (1) Self-Convolution with fast Fourier transform implementation can significantly speed up most of the popular non-local image restoration algorithms, with two-fold to nine-fold faster block matching, and (2) the proposed online multi-modality image restoration scheme achieves superior denoising results than competing methods in both efficiency and effectiveness on RGB-NIR images. The code for this work is publicly available at https://github.com/GuoLanqing/Self-Convolution. [ABSTRACT FROM AUTHOR]

Cartoonization as a special type of artistic style transfer is a difficult image processing task. The current existing artistic style transfer methods cannot generate satisfactory cartoon-style images due to that artistic style images often have delicate strokes and rich hierarchical color changes while cartoon-style images have smooth surfaces without obvious color changes, and sharp edges. To this end, we propose a cartoon loss based generative adversarial network (CartoonLossGAN) for cartoonization. Particularly, we first reuse the encoder part of the discriminator to build a compact generative adversarial network (GAN) based cartoonization architecture. Then we propose a novel cartoon loss function for the architecture. It can imitate the process of sketching to learn the smooth surface of the cartoon image, and imitate the coloring process to learn the coloring of the cartoon image. Furthermore, we also propose an initialization strategy, which is used in the scenario of reusing the discriminator to make our model training easier and more stable. Extensive experimental results demonstrate that our proposed CartoonLossGAN can generate fantastic cartoon-style images, and outperforms four representative methods. [ABSTRACT FROM AUTHOR]

Morphological attribute profiles are multilevel decompositions of images obtained with a sequence of transformations performed by connected operators. They have been extensively employed in performing multi-scale and region-based analysis in a large number of applications. One main, still unresolved, issue is the selection of filter parameters able to provide representative and non-redundant threshold decomposition of the image. This paper presents a framework for the automatic selection of filter thresholds based on Granulometric Characteristic Functions (GCFs). GCFs describe the way that non-linear morphological filters simplify a scene according to a given measure. Since attribute filters rely on a hierarchical representation of an image (e.g., the Tree of Shapes) for their implementation, GCFs can be efficiently computed by taking advantage of the tree representation. Eventually, the study of the GCFs allows the identification of a meaningful set of thresholds. Therefore, a trial and error approach is not necessary for the threshold selection, automating the process and in turn decreasing the computational time. It is shown that the redundant information is reduced within the resulting profiles (a problem of high occurrence, as regards manual selection). The proposed approach is tested on two real remote sensing data sets, and the classification results are compared with strategies present in the literature.

The growth of pollen tubes is of significant interest in plant cell biology, as it provides an understanding of internal cell dynamics that affect observable structural characteristics such as cell diameter, length, and growth rate. However, these parameters can only be measured in experimental videos if the complete shape of the cell is known. The challenge is to accurately obtain the cell boundary in noisy video images. Usually, these measurements are performed by a scientist who manually draws regions-of-interest on the images displayed on a computer screen. In this paper, a new automated technique is presented for boundary detection by fusing fluorescence and brightfield images, and a new efficient method of obtaining the final cell boundary through the process of Seam Carving is proposed. This approach takes advantage of the nature of the fusion process and also the shape of the pollen tube to efficiently search for the optimal cell boundary. In video segmentation, the first two frames are used to initialize the segmentation process by creating a search space based on a parametric model of the cell shape. Updates to the search space are performed based on the location of past segmentations and a prediction of the next segmentation.Experimental results show comparable accuracy to a previous method, but significant decrease in processing time. This has the potential for real time applications in pollen tube microscopy.

We introduce a new chamfering paradigm, locally connecting pixels to produce path distances that approximate Euclidean space by building a small network (a replacement product) inside each pixel. These “ RE-grid graphs” maintain near-Euclidean polygonal distance contours even in noisy data sets, making them useful tools for approximation when exact numerical solutions are unobtainable or impractical. The RE-grid graph creates a modular global architecture with lower pixel-to-pixel valency and simplified topology at the cost of increased computational complexity due to its internal structure. We present an introduction to chamfering replacement products with a number of case study examples to demonstrate the potential of these graphs for path-finding in high frequency and low resolution image spaces which motivate further study. Possible future applications include morphology, watershed segmentation, halftoning, neural network design, anisotropic image processing, image skeletonization, dendritic shaping, and cellular automata. [ABSTRACT FROM AUTHOR]

We introduce a novel edge tracing algorithm using Gaussian process regression. Our edge-based segmentation algorithm models an edge of interest using Gaussian process regression and iteratively searches the image for edge pixels in a recursive Bayesian scheme. This procedure combines local edge information from the image gradient and global structural information from posterior curves, sampled from the model’s posterior predictive distribution, to sequentially build and refine an observation set of edge pixels. This accumulation of pixels converges the distribution to the edge of interest. Hyperparameters can be tuned by the user at initialisation and optimised given the refined observation set. This tunable approach does not require any prior training and is not restricted to any particular type of imaging domain. Due to the model’s uncertainty quantification, the algorithm is robust to artefacts and occlusions which degrade the quality and continuity of edges in images. Our approach also has the ability to efficiently trace edges in image sequences by using previous-image edge traces as a priori information for consecutive images. Various applications to medical imaging and satellite imaging are used to validate the technique and comparisons are made with two commonly used edge tracing algorithms. [ABSTRACT FROM AUTHOR]

We introduce a novel edge tracing algorithm using Gaussian process regression. Our edge-based segmentation algorithm models an edge of interest using Gaussian process regression and iteratively searches the image for edge pixels in a recursive Bayesian scheme. This procedure combines local edge information from the image gradient and global structural information from posterior curves, sampled from the model’s posterior predictive distribution, to sequentially build and refine an observation set of edge pixels. This accumulation of pixels converges the distribution to the edge of interest. Hyperparameters can be tuned by the user at initialisation and optimised given the refined observation set. This tunable approach does not require any prior training and is not restricted to any particular type of imaging domain. Due to the model’s uncertainty quantification, the algorithm is robust to artefacts and occlusions which degrade the quality and continuity of edges in images. Our approach also has the ability to efficiently trace edges in image sequences by using previous-image edge traces as a priori information for consecutive images. Various applications to medical imaging and satellite imaging are used to validate the technique and comparisons are made with two commonly used edge tracing algorithms. [ABSTRACT FROM AUTHOR]

Multi-view clustering aims at simultaneously obtaining a consensus underlying subspace across multiple views and conducting clustering on the learned consensus subspace, which has gained a variety of interest in image processing. In this paper, we propose the Semi-supervised Structured Subspace Learning algorithm for clustering data points from Multiple sources (SSSL-M). We explicitly extend the traditional multi-view clustering with a semi-supervised manner and then build an anti-block-diagonal indicator matrix with small amount of supervisory information to pursue the block-diagonal structure of the shared affinity matrix. SSSL-M regularizes multiple view-specific affinity matrices into a shared affinity matrix based on reconstruction through a unified framework consisting of backward encoding networks and the self-expressive mapping. The shared affinity matrix is comprehensive and can flexibly encode complementary information from multiple view-specific affinity matrices. An enhanced structural consistency of affinity matrices from different views can be achieved and the intrinsic relationships among affinity matrices from multiple views can be effectively reflected in this manner. Technically, we formulate the proposed model as an optimization problem, which can be solved by an alternating optimization scheme. Experimental results over seven different benchmark datasets demonstrate that better clustering results can be obtained by our method compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

We introduce a new chamfering paradigm, locally connecting pixels to produce path distances that approximate Euclidean space by building a small network (a replacement product) inside each pixel. These “ $RE$ -grid graphs” maintain near-Euclidean polygonal distance contours even in noisy data sets, making them useful tools for approximation when exact numerical solutions are unobtainable or impractical. The $RE$ -grid graph creates a modular global architecture with lower pixel-to-pixel valency and simplified topology at the cost of increased computational complexity due to its internal structure. We present an introduction to chamfering replacement products with a number of case study examples to demonstrate the potential of these graphs for path-finding in high frequency and low resolution image spaces which motivate further study. Possible future applications include morphology, watershed segmentation, halftoning, neural network design, anisotropic image processing, image skeletonization, dendritic shaping, and cellular automata. [ABSTRACT FROM AUTHOR]

Online Social Networks (OSNs) have attracted a huge number of users, who store and share various images on a daily basis. As a well-known fact, most OSN platforms apply a series of lossy operations on the uploaded images, which could severely degrade the quality of the shared images, negatively affecting the user experiences. In this work, we consider the problem of significantly improving OSN-shared images through applying an optimal pre-filtering prior to image sharing, without any cooperation from the OSN platform itself. Facebook, as one of the most popular and representative OSNs, is chosen as the platform to present our designed pre-filtering strategy. We first treat Facebook as a black box, and thoroughly recover its mechanism of processing color images. Based on the precise knowledge on the image processing pipeline on Facebook, we design the pre-filter under an optimization framework, minimizing the end-to-end distortion between the shared image and the original one. Compared with the directly shared images, our proposed pre-filtering-then-sharing strategy brings significant improvements in terms of both quantitative and qualitative metrics. Extensive experimental results are provided to show the superiority of our proposed method. Finally, we discuss the strategy on how to extend our proposed technique to other OSN platforms. [ABSTRACT FROM AUTHOR]

This work considers noise removal from images, focusing on the well-known K-SVD denoising algorithm. This sparsity-based method was proposed in 2006, and for a short while it was considered as state-of-the-art. However, over the years it has been surpassed by other methods, including the recent deep-learning-based newcomers. The question we address in this paper is whether K-SVD was brought to its peak in its original conception, or whether it can be made competitive again. The approach we take in answering this question is to redesign the algorithm to operate in a supervised manner. More specifically, we propose an end-to-end deep architecture with the exact K-SVD computational path, and train it for optimized denoising. Our work shows how to overcome difficulties arising in turning the K-SVD scheme into a differentiable, and thus learnable, machine. With a small number of parameters to learn and while preserving the original K-SVD essence, the proposed architecture is shown to outperform the classical K-SVD algorithm substantially, and getting closer to recent state-of-the-art learning-based denoising methods. Adopting a broader context, this work touches on themes around the design of deep-learning solutions for image processing tasks, while paving a bridge between classic methods and novel deep-learning-based ones. [ABSTRACT FROM AUTHOR]

Image processing in hexagonal lattice has many advantages rather than square lattice. Researchers have addressed benefits of hexagonal structure in applications such as binarization, rotation, scaling and edge detection. Approximately all existing hardwares for capturing and displaying images are based on square lattice. Therefore, the best way for using advantages of hexagonal lattice is to find a proper software approach to convert square pixels to hexagonal ones. This paper presents a hexagonal platform based on interpolation which addresses three existing hexagonal challenges including imperfect hexagonal shape, inaccurate intensity level of hexagonal pixels and lower resolution in hexagonal space. The proposed interpolation is computed by overlaps between square and hexagonal pixels. Overlap types are formulated mathematically in 8 separate cases. Each overlap case is detected automatically and used to compute final gray-level intensity of hexagonal pixels. It is mathematically and experimentally shown that the proposed method satisfies necessary conditions for square-to-hexagonal conversion. The proposed scheme is evaluated on synthetic and real images with 10 different levels of noise in interpolation and edge detection applications. In synthetic images, the proposed method achieves the best figure of merit (FOM) 99.92% and 98.67% in high and low SNRs 100 and 20, respectively. Also, the proposed method outperforms existing state of the art hexagonal lattices with interclass correlation coefficient (ICC) 84.18% and mean rating 7.7 (out of 9) in real images. [ABSTRACT FROM AUTHOR]

Face hallucination or super-resolution is a practical application of general image super-resolution which has been recently studied by many researchers. The challenge of good face hallucination comes from a variety of poses, illuminations, facial expressions, and other degradations. In many proposed methods, researchers resolve it by using a generative neural network to reduce the perceptual loss so we can generate a photo-realistic image. The problem is that researchers usually overlook the fidelity of the super-resolved image which could affect further facial image processing. Meanwhile, many CNN based approaches cascade multiple networks to extract facial prior information to improve super-resolution quality. Because of the end-to-end design, the details are missing for investigation. In this paper, we combine new techniques in convolutional neural network and random forests to a Hierarchical CNN based Random Forests (HCRF) approach for face super-resolution in a coarse-to-fine manner. In the proposed approach, we focus on a general approach that can handle facial images with various conditions without pre-processing. To the best of our knowledge, this is the first paper that combines the advantages of deep learning with random forests for face super-resolution. To achieve superior performance, we propose two novel CNN models for coarse facial image super-resolution and segmentation and then apply new random forests to target on local facial features refinement making use of the segmentation results. Extensive benchmark experiments on subjective and objective evaluation show that HCRF can achieve comparable speed and competitive performance compared with state-of-the-art super-resolution approaches for very low-resolution images. [ABSTRACT FROM AUTHOR]

In recent years, Salient Object Detection (SOD) has shown great success with the achievements of large-scale benchmarks and deep learning techniques. However, existing SOD methods mainly focus on natural images with low-resolutions, e.g., $400\times 400$ or less. This drawback hinders them for advanced practical applications, which need high-resolution, detail-aware results. Besides, lacking of the boundary detail and semantic context of salient objects is also a key concern for accurate SOD. To address these issues, in this work we focus on the High-Resolution Salient Object Detection (HRSOD) task. Technically, we propose the first end-to-end learnable framework, named Dual ReFinement Network (DRFNet), for fully automatic HRSOD. More specifically, the proposed DRFNet consists of a shared feature extractor and two effective refinement heads. By decoupling the detail and context information, one refinement head adopts a global-aware feature pyramid. Without increasing too much computational burden, it can boost the spatial detail information, which narrows the gap between high-level semantics and low-level details. In parallel, the other refinement head adopts hybrid dilated convolutional blocks and group-wise upsamplings, which are very efficient in extracting contextual information. Based on the dual refinements, our approach can enlarge receptive fields and obtain more discriminative features from high-resolution images. Experimental results on high-resolution benchmarks (the public DUT-HRSOD and the proposed DAVIS-SOD) demonstrate that our method is not only efficient but also performs more accurate than other state-of-the-arts. Besides, our method generalizes well on typical low-resolution benchmarks. [ABSTRACT FROM AUTHOR]

Inverse problems are a group of important mathematical problems that aim at estimating source data $x$ and operation parameters $z$ from inadequate observations $y$. In the image processing field, most recent deep learning-based methods simply deal with such problems under a pixel-wise regression framework (from $y$ to $x$) while ignoring the physics behind. In this paper, we re-examine these problems under a different viewpoint and propose a novel framework for solving certain types of inverse problems in image processing. Instead of predicting $x$ directly from $y$ , we train a deep neural network to estimate the degradation parameters $z$ under an adversarial training paradigm. We show that if the degradation behind satisfies some certain assumptions, the solution to the problem can be improved by introducing additional adversarial constraints to the parameter space and the training may not even require pair-wise supervision. In our experiment, we apply our method to a variety of real-world problems, including image denoising, image deraining, image shadow removal, non-uniform illumination correction, and underdetermined blind source separation of images or speech signals. The results on multiple tasks demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Higher Order Aberrations (HOAs) are complex refractive errors in the human eye that cannot be corrected by regular lens systems. Researchers have developed numerous approaches to analyze the effect of these refractive errors; the most popular among these approaches use Zernike polynomial approximation to describe the shape of the wavefront of light exiting the pupil after it has been altered by the refractive errors. We use this wavefront shape to create a linear imaging system that simulates how the eye perceives source images at the retina. With phase information from this system, we create a second linear imaging system to modify source images so that they would be perceived by the retina without distortion. By modifying source images, the visual process cascades two optical systems before the light reaches the retina, a technique that counteracts the effect of the refractive errors. While our method effectively compensates for distortions induced by HOAs, it also introduces blurring and loss of contrast; a problem that we address with Total Variation Regularization. With this technique, we optimize source images so that they are perceived at the retina as close as possible to the original source image. To measure the effectiveness of our methods, we compute the Euclidean error between the source images and the images perceived at the retina. When comparing our results with existing corrective methods that use deconvolution and total variation regularization, we achieve an average of 50% reduction in error with lower computational costs. [ABSTRACT FROM AUTHOR]

Traditional image signal processing (ISP) pipeline consists of a set of cascaded image processing modules onboard a camera to reconstruct a high-quality sRGB image from the sensor raw data. Recently, some methods have been proposed to learn a convolutional neural network (CNN) to improve the performance of traditional ISP. However, in these works usually a CNN is directly trained to accomplish the ISP tasks without considering much the correlation among the different components in an ISP. As a result, the quality of reconstructed images is barely satisfactory in challenging scenarios such as low-light imaging. In this paper, we firstly analyze the correlation among the different tasks in an ISP, and categorize them into two weakly correlated groups: restoration and enhancement. Then we design a two-stage network, called CameraNet, to progressively learn the two groups of ISP tasks. In each stage, a ground truth is specified to supervise the subnetwork learning, and the two subnetworks are jointly fine-tuned to produce the final output. Experiments on three benchmark datasets show that the proposed CameraNet achieves consistently compelling reconstruction quality and outperforms the recently proposed ISP learning methods. [ABSTRACT FROM AUTHOR]

Plant disease diagnosis is very critical for agriculture due to its importance for increasing crop production. Recent advances in image processing offer us a new way to solve this issue via visual plant disease analysis. However, there are few works in this area, not to mention systematic researches. In this paper, we systematically investigate the problem of visual plant disease recognition for plant disease diagnosis. Compared with other types of images, plant disease images generally exhibit randomly distributed lesions, diverse symptoms and complex backgrounds, and thus are hard to capture discriminative information. To facilitate the plant disease recognition research, we construct a new large-scale plant disease dataset with 271 plant disease categories and 220,592 images. Based on this dataset, we tackle plant disease recognition via reweighting both visual regions and loss to emphasize diseased parts. We first compute the weights of all the divided patches from each image based on the cluster distribution of these patches to indicate the discriminative level of each patch. Then we allocate the weight to each loss for each patch-label pair during weakly-supervised training to enable discriminative disease part learning. We finally extract patch features from the network trained with loss reweighting, and utilize the LSTM network to encode the weighed patch feature sequence into a comprehensive feature representation. Extensive evaluations on this dataset and another public dataset demonstrate the advantage of the proposed method. We expect this research will further the agenda of plant disease recognition in the community of image processing. [ABSTRACT FROM AUTHOR]

Noise type and strength estimation are important in many image processing applications like denoising, compression, video tracking, etc. There are many existing methods for estimation of the type of noise and its strength in digital images. These methods mostly rely on the transform or spatial domain information of images. We propose a hybrid Discrete Wavelet Transform (DWT) and edge information removal based algorithm to estimate the strength of Gaussian noise in digital images. The wavelet coefficients corresponding to spatial domain edges are excluded from noise estimate calculation using a Sobel edge detector. The accuracy of the proposed algorithm is further increased using polynomial regression. Parseval’s theorem mathematically validates the proposed algorithm. The performance of the proposed algorithm is evaluated on a standard LIVE image dataset. Benchmarking results show that the proposed algorithm outperforms all other state of the art algorithms by a large margin over a wide range of noise. [ABSTRACT FROM AUTHOR]

Superpixel segmentation, as a central image processing task, has many applications in computer vision and computer graphics. Boundary alignment and shape compactness are leading indicators to evaluate a superpixel segmentation algorithm. Furthermore, convexity can make superpixels reflect more geometric structures in images and provide a more concise over-segmentation result. In this paper, we consider generating convex and compact superpixels while satisfying the constraints of adhering to the boundary as far as possible. We formulate the new superpixel segmentation into an edge-constrained centroidal power diagram (ECCPD) optimization problem. In the implementation, we optimize the superpixel configurations by repeatedly performing two alternative operations, which include site location updating and weight updating through a weight function defined by image features. Compared with existing superpixel methods, our method can partition an image into fully convex and compact superpixels with better boundary adherence. Extensive experimental results show that our approach outperforms existing superpixel segmentation methods in boundary alignment and compactness for generating convex superpixels. [ABSTRACT FROM AUTHOR]

The ubiquitous presence of surveillance cameras severely compromises the security of private information (e.g. passwords) entered via a conventional keyboard interface in public places. We address this problem by proposing dual modulated QR (DMQR) codes, a novel QR code extension via which users can securely communicate private information in public places using their smartphones and a camera interface. Dual modulated QR codes use the same synchronization patterns and module geometry as conventional monochrome QR codes. Within each module, primary data is embedded using intensity modulation compatible with conventional QR code decoding. Specifically, depending on the bit to be embedded, a module is either left white or an elliptical black dot is placed within it. Additionally, for each module containing an elliptical dot, secondary data is embedded by orientation modulation; that is, by using different orientations for the elliptical dots. Because the orientation of the elliptical dots can only be reliably assessed when the barcodes are captured from a close distance, the secondary data provides “proximal privacy” and can be effectively used to communicate private information securely in public settings. Tests conducted using several alternative parameter settings demonstrate that the proposed DMQR codes are effective in meeting their objective– the secondary data can be accurately decoded for short capture distances (6 in.) but cannot be recovered from images captured over long distances (>12 in.). Furthermore, the proximal privacy can be adapted to application needs by varying the eccentricity of the elliptical dots used. [ABSTRACT FROM AUTHOR]

Cover-lossless robust watermarking is a new research issue in the information hiding community, which can restore the cover image completely in case of no attacks. Most countermeasures proposed in the literature usually focus on additive noise-like manipulations such as JPEG compression, low-pass filtering and Gaussian additive noise, but few are resistant to challenging geometric deformations such as rotation and scaling. The main reason is that in the existing cover-lossless robust watermarking algorithms, those exploited robust features are related to the pixel position. In this article, we present a new cover-lossless robust image watermarking method by efficiently embedding a watermark into low-order Zernike moments and reversibly hiding the distortion due to the robust watermark as the compensation information for restoration of the cover image. The amplitude of the exploited low-order Zernike moments are: 1) mathematically invariant to scaling the size of an image and rotation with any angle; and 2) robust to interpolation errors during geometric transformations, and those common image processing operations. To reduce the compensation information, the robust watermarking process is elaborately and luminously designed by using the quantized error, the watermarked error and the rounded error to represent the difference between the original and the robust watermarked image. As a result, a cover-lossless robust watermarking system against geometric deformations is achieved with good performance. Experimental results show that the proposed robust watermarking method can effectively reduce the compensation information, and the new cover-lossless robust watermarking system provides strong robustness to those content-preserving manipulations including scaling, rotation, JPEG compression and other noise-like manipulations. In case of no attacks, the cover image can be recovered without any loss. [ABSTRACT FROM AUTHOR]

Fog removal from an image is an active research topic in computer vision. However, current literature is weak in the following two areas which in many ways are hindering progress for developing defogging algorithms. First, there is no true real-world and naturally occurring foggy image datasets suitable for developing defogging models. Second, there is no suitable mathematically simple and easy to use image quality assessment (IQA) methods for evaluating the visual quality of defogged images. We address these two aspects in this paper. We first introduce a new foggy image dataset called multiple real-world foggy image dataset (MRFID). MRFID contains foggy and clear images of 200 outdoor scenes. For each scene, one clear image and 4 foggy images of different densities defined as slightly foggy, moderately foggy, highly foggy, and extremely foggy, are manually selected from images taken from these scenes over the course of one calendar year. We then process the foggy images of MRFID using 16 defogging methods to obtain 12,800 defogged images (DFIs) and perform a comprehensive subjective evaluation of the visual quality of the DFIs. Through collecting the mean opinion score (MOS) of 120 subjects and evaluating a variety of fog-relevant image features, we have developed a new Fog-relevant Feature based SIMilarity index (FRFSIM) for assessing the visual quality of DFIs. We present extensive experimental results to show that our new visual quality assessment measure, the FRFSIM, is more consistent with the MOS than other IQA methods and is therefore more suitable for evaluating defogged images than other state-of-the-art IQA methods. Our dataset and relevant code are available at http://www.vistalab.ac.cn/MRFID-for-defogging/. [ABSTRACT FROM AUTHOR]

In this paper we combine video compression and modern image processing methods. Iterative filter methods for prediction signals based on classic inpainting methods are introduced and extensive parameter tests are described. In order to construct an alternative prediction filter for video coding, techniques originally employed for inpainting are applied. Thereby, the structures of the underlying prediction were incorporated into the filter construction making it signal adaptive. The resulting optimization problem is solved using the so-called Alternating Direction Method of Multipliers (ADMM). The undertaken novel parameter tests are described and it is shown that they improve the coding efficiency of the tool. The suggested filter is embedded into a software based on HEVC with additional QTBT (Quadtree plus Binary Tree) and MTT (Multi-Type-Tree) block structure. Overall, the proposed filter method obtains average bitrate savings of 1.35% at an average encoder runtime increase of 28% and decoder runtime increase of 38%. UHD test sequences achieve bitrate savings of up to 3.66% for Random Access. [ABSTRACT FROM AUTHOR]

Generating realistic images with the guidance of reference images and human poses is challenging. Despite the success of previous works on synthesizing person images in the iconic views, no efforts are made towards the task of pose-guided image synthesis in the non-iconic views. Particularly, we find that previous models cannot handle such a complex task, where the person images are captured in the non-iconic views by commercially-available digital cameras. To this end, we propose a new framework – Multi-branch Refinement Network (MR-Net), which utilizes several visual cues, including target person poses, foreground person body and scene images parsed. Furthermore, a novel Region of Interest (RoI) perceptual loss is proposed to optimize the MR-Net. Extensive experiments on two non-iconic datasets, Penn Action and BBC-Pose, as well as an iconic dataset – Market-1501, show the efficacy of the proposed model that can tackle the problem of pose-guided person image generation from the non-iconic views. The data, models, and codes are downloadable from https://github.com/loadder/MR-Net. [ABSTRACT FROM AUTHOR]

Existing neural networks proposed for low-level image processing tasks are usually implemented by stacking convolution layers with limited kernel size. Every convolution layer merely involves in context information from a small local neighborhood. More contextual features can be explored as more convolution layers are adopted. However it is difficult and costly to take full advantage of long-range dependencies. We propose a novel non-local module, Pyramid Non-local Block, to build up connection between every pixel and all remain pixels. The proposed module is capable of efficiently exploiting pairwise dependencies between different scales of low-level structures. The target is fulfilled through first learning a query feature map with full resolution and a pyramid of reference feature maps with downscaled resolutions. Then correlations with multi-scale reference features are exploited for enhancing pixel-level feature representation. The calculation procedure is economical considering memory consumption and computational cost. Based on the proposed module, we devise a Pyramid Non-local Enhanced Networks for edge-preserving image smoothing which achieves state-of-the-art performance in imitating three classical image smoothing algorithms. Additionally, the pyramid non-local block can be directly incorporated into convolution neural networks for other image restoration tasks. We integrate it into two existing methods for image denoising and single image super-resolution, achieving consistently improved performance. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have been extensively applied in image processing, including visual saliency map prediction of images. A major difficulty in using a DNN for visual saliency prediction is the lack of labeled ground truth of visual saliency. A powerful DNN usually contains a large number of trainable parameters. This condition can easily lead to model over-fitting. In this study, we develop a novel method that overcomes such difficulty by embedding hierarchical knowledge of existing visual saliency models in a DNN. We achieve the objective of exploiting the knowledge contained in the existing visual saliency models by using saliency maps generated by local, global, and semantic models to tune and fix about 92.5% of the parameters in our network in a hierarchical manner. As a result, the number of trainable parameters that need to be tuned by the ground truth is considerably reduced. This reduction enables us to fully utilize the power of a large DNN and overcome the issue of over-fitting at the same time. Furthermore, we introduce a simple but very effective center prior in designing the learning cost function of the DNN by attaching high importance to the errors around the image center. We also present extensive experimental results on four commonly used public databases to demonstrate the superiority of the proposed method over classical and state-of-the-art methods on various evaluation metrics. [ABSTRACT FROM AUTHOR]

We introduce BSD-GAN, a novel multi-branch and scale-disentangled training method which enables unconditional Generative Adversarial Networks (GANs) to learn image representations at multiple scales, benefiting a wide range of generation and editing tasks. The key feature of BSD-GAN is that it is trained in multiple branches, progressively covering both the breadth and depth of the network, as resolutions of the training images increase to reveal finer-scale features. Specifically, each noise vector, as input to the generator network of BSD-GAN, is deliberately split into several sub-vectors, each corresponding to, and is trained to learn, image representations at a particular scale. During training, we progressively “de-freeze” the sub-vectors, one at a time, as a new set of higher-resolution images is employed for training and more network layers are added. A consequence of such an explicit sub-vector designation is that we can directly manipulate and even combine latent (sub-vector) codes which model different feature scales. Extensive experiments demonstrate the effectiveness of our training method in scale-disentangled learning of image representations and synthesis of novel image contents, without any extra labels and without compromising quality of the synthesized high-resolution images. We further demonstrate several image generation and manipulation applications enabled or improved by BSD-GAN. [ABSTRACT FROM AUTHOR]

Multi-view subspace clustering has been applied to applications such as image processing and video surveillance, and has attracted increasing attention. Most existing methods learn view-specific self-representation matrices, and construct a combined affinity matrix from multiple views. The affinity construction process is time-consuming, and the combined affinity matrix is not guaranteed to reflect the whole true subspace structure. To overcome these issues, the Latent Complete Row Space Recovery (LCRSR) method is proposed. Concretely, LCRSR is based on the assumption that the multi-view observations are generated from an underlying latent representation, which is further assumed to collect the authentic samples drawn exactly from multiple subspaces. LCRSR is able to recover the row space of the latent representation, which not only carries complete information from multiple views but also determines the subspace membership under certain conditions. LCRSR does not involve the graph construction procedure and is solved with an efficient and convergent algorithm, thereby being more scalable to large-scale datasets. The effectiveness and efficiency of LCRSR are validated by clustering various kinds of multi-view data and illustrated in the background subtraction task. [ABSTRACT FROM AUTHOR]

Regularization-based image restoration is one of the most powerful tools in image processing and computer vision thanks to its flexibility for handling various inverse problems. However, designing an optimal regularization function still remains unsolved since natural images and related scene types have a complex structure. In this paper, we present a general and principled framework, called deeply aggregated alternating minimization (DeepAM). We design a convolutional neural network (CNN) to implicitly parameterize the regularizer of the alternating minimization (AM) algorithm. Contrary to the conventional AM algorithm based on a point-wise proximal mapping, the DeepAM projects intermediate estimate into a set of natural images via deep aggregation. Since the CNN is fully integrated into the AM procedure, all parameters can be jointly optimized through end-to-end training. These properties enable the DeepAM to converge with a small number of iterations, while maintaining an algorithmic simplicity. We show that the DeepAM outperforms state-of-the-art methods, including nonlocal-based methods, Plug-and-Play regularization, and recent data-driven approaches. The effectiveness of our framework is demonstrated in a variety of image restoration tasks: Guassian denoising, deraining, deblurring, super-resolution, color-guided depth upsampling, and RGB/NIR restoration. [ABSTRACT FROM AUTHOR]

Traditional image processing operators often provide some control parameters to tweak the final results. Recently, different convolutional neural networks have been used to approximate or improve these operators. However, in those methods, one single model can only handle one operator of a specific parameter value and does not support parameter tuning. In this paper, we propose a new plugin module, “Adaptive Filterbank Pyramid”, which can be inserted into a backbone network to support multiple operators and continuous parameter tuning. Our module explicitly represents one operator with one filterbank pyramid. To generate the results of a specific operator, the corresponding filterbank pyramid is convolved with the intermediate feature pyramid produced by the backbone network. The weights of the filterbank pyramid are directly regressed by another sub-network, which is jointly trained with the backbone network and adapted to the input parameter, thus enabling continuous parameter tuning. We applied the proposed module for a large variety of image processing tasks, including image smoothing, image denoising, image deblocking, image enhancement and neural style transfer. Experiments show that our method is generalized to different types of image processing tasks and different backbone network structures. Compared to the single-operator-single-parameter baseline, our method can produce comparable results but is significantly more efficient in both training and testing. [ABSTRACT FROM AUTHOR]

Low-light image enhancement is a challenging task that has attracted considerable attention. Pictures taken in low-light conditions often have bad visual quality. To address the problem, we regard the low-light enhancement as a residual learning problem that is to estimate the residual between low- and normal-light images. In this paper, we propose a novel Deep Lightening Network (DLN) that benefits from the recent development of Convolutional Neural Networks (CNNs). The proposed DLN consists of several Lightening Back-Projection (LBP) blocks. The LBPs perform lightening and darkening processes iteratively to learn the residual for normal-light estimations. To effectively utilize the local and global features, we also propose a Feature Aggregation (FA) block that adaptively fuses the results of different LBPs. We evaluate the proposed method on different datasets. Numerical results show that our proposed DLN approach outperforms other methods under both objective and subjective metrics. [ABSTRACT FROM AUTHOR]

Sparse representation has achieved great success in various image processing and computer vision tasks. For image processing, typical patch-based sparse representation (PSR) models usually tend to generate undesirable visual artifacts, while group-based sparse representation (GSR) models lean to produce over-smooth effects. In this paper, we propose a new sparse representation model, termed joint patch-group based sparse representation (JPG-SR). Compared with existing sparse representation models, the proposed JPG-SR provides an effective mechanism to integrate the local sparsity and nonlocal self-similarity of images. We then apply the proposed JPG-SR to image restoration tasks, including image inpainting and image deblocking. An iterative algorithm based on the alternating direction method of multipliers (ADMM) framework is developed to solve the proposed JPG-SR based image restoration problems. Experimental results demonstrate that the proposed JPG-SR is effective and outperforms many state-of-the-art methods in both objective and perceptual quality. [ABSTRACT FROM AUTHOR]

With the advancement of image processing and computer vision technology, content-based product search is applied in a wide variety of common tasks, such as online shopping, automatic checkout systems, and intelligent logistics. Given a product image as a query, existing product search systems mainly perform the retrieval process using predefined databases with fixed product categories. However, real-world applications often require inserting new categories or updating existing products in the product database. When using existing product search methods, the image feature extraction models must be retrained and database indexes must be rebuilt to accommodate the updated data, and these operations incur high costs for data annotation and training time. To this end, we propose a few-shot incremental product search framework with meta-learning, which requires very few annotated images and has a reasonable training time. In particular, our framework contains a multipooling-based product feature extractor that learns a discriminative representation for each product, and we also design a meta-learning-based feature adapter to guarantee the robustness of the few-shot features. Furthermore, when expanding new categories in batches during a product search, we reconstruct the few-shot features by using an incremental weight combiner to accommodate the incremental search task. Through extensive experiments, we demonstrate that the proposed framework achieves excellent performance for new products while still guaranteeing the high search accuracy of the base categories after gradually expanding new product categories without forgetting. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image segmentation is currently of great importance in image processing for remote sensing applications. However, it is a challenging task due to two main reasons. Firstly, the label information is difficult to acquire due to high annotation costs. Secondly, the speckle effect embedded in the PolSAR imaging process remarkably degrades the segmentation performance. To address these two issues, we present a contextual PolSAR image semantic segmentation method in this paper. With a newly defined channel-wise consistent feature set as input, the three-dimensional discrete wavelet transform (3D-DWT) technique is employed to extract discriminative multi-scale features that are robust to speckle noise. Then Markov random field (MRF) is further applied to enforce label smoothness spatially during segmentation. By simultaneously utilizing 3D-DWT features and MRF priors for the first time, contextual information is fully integrated during the segmentation to ensure accurate and smooth segmentation. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on three real benchmark PolSAR image data sets. Experimental results indicate that the proposed method achieves promising segmentation accuracy and preferable spatial consistency using a minimal number of labeled pixels. [ABSTRACT FROM AUTHOR]

Generating text to have a consistent style with only a few observed highly-stylized text samples is a difficult task for image processing. The text style involving the typography, i.e., font, stroke, color, decoration, effects, etc., should be considered for transfer. In this paper, we propose a novel approach to stylize target text by decoding weighted deep features from only a few referenced samples. The deep features, including content and style features of each referenced text, are extracted from a Convolutional Neural Network (CNN) that is optimized for character recognition. Then, we calculate the similarity scores of the target text and the referenced samples by measuring the distance along the corresponding channels from the content features of the CNN when considering only the content, and assign them as the weights for aggregating the deep features. To enforce the stylized text to be realistic, a discriminative network with adversarial loss is employed. We demonstrate the effectiveness of our network by conducting experiments on three different datasets which have various styles, fonts, languages, etc. Additionally, the coefficients for character style transfer, including the character content, the effect of similarity matrix, the number of referenced characters, the similarity between characters, and performance evaluation by a new protocol are analyzed for better understanding our proposed framework. [ABSTRACT FROM AUTHOR]

Image deraining is an important yet challenging image processing task. Though deterministic image deraining methods are developed with encouraging performance, they are infeasible to learn flexible representations for probabilistic inference and diverse predictions. Besides, rain intensity varies both in spatial locations and across color channels, making this task more difficult. In this paper, we propose a Conditional Variational Image Deraining (CVID) network for better deraining performance, leveraging the exclusive generative ability of Conditional Variational Auto-Encoder (CVAE) on providing diverse predictions for the rainy image. To perform spatially adaptive deraining, we propose a spatial density estimation (SDE) module to estimate a rain density map for each image. Since rain density varies across different color channels, we also propose a channel-wise (CW) deraining scheme. Experiments on synthesized and real-world datasets show that the proposed CVID network achieves much better performance than previous deterministic methods on image deraining. Extensive ablation studies validate the effectiveness of the proposed SDE module and CW scheme in our CVID network. The code is available at https://github.com/Yingjun-Du/VID. [ABSTRACT FROM AUTHOR]