Search

A densely-sampled light field (LF) is highly desirable in various applications, such as 3-D reconstruction, post-capture refocusing and virtual reality. However, it is costly to acquire such data. Although many computational methods have been proposed to reconstruct a densely-sampled LF from a sparsely-sampled one, they still suffer from either low reconstruction quality, low computational efficiency, or the restriction on the regularity of the sampling pattern. To this end, we propose a novel learning-based method, which accepts sparsely-sampled LFs with irregular structures, and produces densely-sampled LFs with arbitrary angular resolution accurately and efficiently. We also propose a simple yet effective method for optimizing the sampling pattern. Our proposed method, an end-to-end trainable network, reconstructs a densely-sampled LF in a coarse-to-fine manner. Specifically, the coarse sub-aperture image (SAI) synthesis module first explores the scene geometry from an unstructured sparsely-sampled LF and leverages it to independently synthesize novel SAIs, in which a confidence-based blending strategy is proposed to fuse the information from different input SAIs, giving an intermediate densely-sampled LF. Then, the efficient LF refinement module learns the angular relationship within the intermediate result to recover the LF parallax structure. Comprehensive experimental evaluations demonstrate the superiority of our method on both real-world and synthetic LF images when compared with state-of-the-art methods. In addition, we illustrate the benefits and advantages of the proposed approach when applied in various LF-based applications, including image-based rendering and depth estimation enhancement., 17 pages, 11 figures, 10 tables

Constrained spectral clustering (SC) based on pairwise constraint propagation has attracted much attention due to the good performance. All the existing methods could be generally cast as the following two steps, i.e., a small number of pairwise constraints are first propagated to the whole data under the guidance of a predefined affinity matrix, and the affinity matrix is then refined in accordance with the resulting propagation and finally adopted for SC. Such a stepwise manner, however, overlooks the fact that the two steps indeed depend on each other, i.e., the two steps form a "chicken-egg" problem, leading to suboptimal performance. To this end, we propose a joint PCP model for constrained SC by simultaneously learning a propagation matrix and an affinity matrix. Especially, it is formulated as a bounded symmetric graph regularized low-rank matrix completion problem. We also show that the optimized affinity matrix by our model exhibits an ideal appearance under some conditions. Extensive experimental results in terms of constrained SC, semisupervised classification, and propagation behavior validate the superior performance of our model compared with state-of-the-art methods.

This paper presents a new full-reference image quality assessment (IQA) method for conducting the perceptual quality evaluation of the light field (LF) images, called the symmetry and depth feature-based model (SDFM). Specifically, the radial symmetry transform is first employed on the luminance components of the reference and distorted LF images to extract their symmetry features for capturing the spatial quality of each view of an LF image. Second, the depth feature extraction scheme is designed to explore the geometry information inherited in an LF image for modeling its LF structural consistency across views. The similarity measurements are subsequently conducted on the comparison of their symmetry and depth features separately, which are further combined to achieve the quality score for the distorted LF image. Note that the proposed SDFM that explores the symmetry and depth features is conformable to the human vision system, which identifies the objects by sensing their structures and geometries. Extensive simulation results on the dense light fields dataset have clearly shown that the proposed SDFM outperforms multiple classical and recently developed IQA algorithms on quality evaluation of the LF images.

In recent years, sparse representation has been successfully utilized for video summarization (VS). However, most of the sparse representation based VS methods characterize each video frame with global features. As a result, some important local details could be neglected by global features, which may compromise the performance of summarization. In this paper, we propose to partition each video frame into a number of patches and characterize each patch with global features. Instead of concatenating the features of each patch and utilizing conventional sparse representation, we formulate the VS problem with such video frame representation as block sparse representation by considering each video frame as a block containing a number of patches. By taking the reconstruction constraint into account, we devise a simultaneous version of block-based OMP (Orthogonal Matching Pursuit) algorithm, namely SBOMP, to solve the proposed model. The proposed model is further extended to a neighborhood based model which considers temporally adjacent frames as a super block. This is one of the first sparse representation based VS methods taking both spatial and temporal contexts into account with blocks. Experimental results on two widely used VS datasets have demonstrated that our proposed methods present clear superiority over existing sparse representation based VS methods and are highly comparable to some deep learning ones requiring supervision information for extra model training.

Correlation filter has demonstrated the power in object tracking, benefiting from its superior speed and competitive performance. However, existing correlation filter based trackers (CFTs) are fragile for some inherent defects caused by the boundary effect. To address this issue, we propose a novel correlation filter based tracking framework by integrating three highly collaborative components, including a fast target proposal module, a distractor-aware filter, and a correlation filter based refiner. Specifically, the target proposal aims at determining some target-like regions in contexts efficiently, which provides target-like patches to learn a distractor-aware filter and detect. Multi-region strategy enlarges space fields for learning and prediction. The filter learned from both target and distractors enhances its ability to identify background. Therefore, our method is capable of evaluating multiple candidates in wider context with less risk of drifting to distractors, namely multi-anchor detection. Besides, the proposed Proposal-Detect-Refine hierarchical searching process progressively achieves data alignment between testing and training samples, which benefits for reliable model prediction. A refiner is used to fine-tune positions after multi-anchor detection for lessening error accumulation and preventing model from drifting. Comprehensive experiments on five challenging datasets, i.e. OTB2013, OTB2015, VOT2017, VOT19, and TC128, demonstrate that the proposed method achieves superior performance against the state-of-the-art methods.

Depth information has been demonstrated to be useful for saliency detection. However, the existing methods for RGBD saliency detection mainly focus on designing straightforward and comprehensive models, while ignoring the transferable ability of the existing RGB saliency detection models. In this article, we propose a novel depth-guided transformation model (DTM) going from RGB saliency to RGBD saliency. The proposed model includes three components, that is: 1) multilevel RGBD saliency initialization; 2) depth-guided saliency refinement; and 3) saliency optimization with depth constraints. The explicit depth feature is first utilized in the multilevel RGBD saliency model to initialize the RGBD saliency by combining the global compactness saliency cue and local geodesic saliency cue. The depth-guided saliency refinement is used to further highlight the salient objects and suppress the background regions by introducing the prior depth domain knowledge and prior refined depth shape. Benefiting from the consistency of the entire object in the depth map, we formulate an optimization model to attain more consistent and accurate saliency results via an energy function, which integrates the unary data term, color smooth term, and depth consistency term. Experiments on three public RGBD saliency detection benchmarks demonstrate the effectiveness and performance improvement of the proposed DTM from RGB to RGBD saliency.

The explosive growth of video data has raised new challenges for many video processing tasks such as video browsing and retrieval, hence, effective and efficient video summarization (VS) is urgently demanded to automatically summarize a video into a succinct version. Recent years have witnessed the advancements of sparse representation based approaches for VS. However, video frames are analyzed individually for keyframe selection in existing methods, which could lead to redundancy among selected keyframes and poor robustness to outlier frames. Due to that adjacent frames are visually similar, candidate keyframes often occur in temporal blocks, in addition to sparse presence. Therefore, in this paper, the block-sparsity of candidate keyframes is taken into consideration, by which the VS problem is formulated as a block sparse dictionary selection model. Moreover, a simultaneous block version of Orthogonal Matching Pursuit (SBOMP) algorithm is designed for model optimization. Two keyframe selection strategies are also explored for each block. Experimental results on two benchmark datasets, namely VSumm and TVSum datasets, demonstrate that the proposed SBOMP based VS method clearly outperforms several state-of-the-art sparse representation based methods in terms of F-score, redundancy among keyframes and robustness to outlier frames.

3D point clouds associated with attributes are considered as a promising paradigm for immersive communication. However, the corresponding compression schemes for this media are still in the infant stage. Moreover, in contrast to conventional image/video compression, it is a more challenging task to compress 3D point cloud data, arising from the irregular structure. In this paper, we propose a novel and effective compression scheme for the attributes of voxelized 3D point clouds. In the first stage, an input voxelized 3D point cloud is divided into blocks of equal size. Then, to deal with the irregular structure of 3D point clouds, a geometry-guided sparse representation (GSR) is proposed to eliminate the redundancy within each block, which is formulated as an ℓ0-norm regularized optimization problem. Also, an inter-block prediction scheme is applied to remove the redundancy between blocks. Finally, by quantitatively analyzing the characteristics of the resulting transform coefficients by GSR, an effective entropy coding strategy that is tailored to our GSR is developed to generate the bitstream. Experimental results over various benchmark datasets show that the proposed compression scheme is able to achieve better rate-distortion performance and visual quality, compared with state-of-the-art methods. This work was supported in part by the National Natural Science Foundation of China under Grant 61871434, Grant 61871342, and Grant 61571274, in part by the Natural Science Foundation for Outstanding Young Scholars of Fujian Province under Grant 2019J06017, in part by the Hong Kong RGC Early Career Scheme Funds under Grant 9048123, in part by the Shandong Provincial Key Research and Development Plan under Grant 2017CXGC150, in part by the Fujian-100 Talented People Program, in part by the High-level Talent Innovation Program of Quanzhou City under Grant 2017G027, in part by the Promotion Program for Young and Middle-aged Teacher in Science and Technology Research of Huaqiao University under Grant ZQN-YX403, and in part by the High-Level Talent Project Foundation of Huaqiao University under Grant 14BS201 and Grant14BS204. Part of this article was presented at the IEEE ICASSP2017

Correlation filter (CF) based trackers have shown promising performance in object tracking. However, both the accuracy and efficiency of existing CF based trackers are limited. In this paper, we propose a robust and real-time object tracking framework, based on a canonical CF tracker. Specifically, we first propose an adaptive model update strategy for preventing the tracker from being contaminated when the target is occluded or disappears in sight. Then, we propose a multimodal validation method for reducing tracking failures, which is capable of generating potential candidates adaptively and evaluating them with a siamese network. In addition, we build a template library online to augment the discriminability of the employed siamese network. Experimental results over OTB-13 and OTB-15 benchmark datasets demonstrate that our method outperforms state-of-the-art ones. Especially, on OTB-15, our method not only achieves a relative gain of 12.3% in AUC score but also runs at a high tracking speed, i.e., 58.3 frames per second, in comparison with the baseline CF tracker.

Nonnegative matrix factorization (NMF) is a well-known paradigm for data representation. Traditional NMF-based classification methods first perform NMF or one of its variants on input data samples to obtain their low-dimensional representations, which are successively classified by means of a typical classifier [e.g., $k$ -nearest neighbors (KNN) and support vector machine (SVM)]. Such a stepwise manner may overlook the dependency between the two processes, resulting in the compromise of the classification accuracy. In this paper, we elegantly unify the two processes by formulating a novel constrained optimization model, namely dual embedding regularized NMF (DENMF), which is semi-supervised. Our DENMF solution simultaneously finds the low-dimensional representations and assignment matrix via joint optimization for better classification. Specifically, input data samples are projected onto a couple of low-dimensional spaces (i.e., feature and label spaces), and locally linear embedding is employed to preserve the identical local geometric structure in different spaces. Moreover, we propose an alternating iteration algorithm to solve the resulting DENMF, whose convergence is theoretically proven. Experimental results over five benchmark datasets demonstrate that DENMF can achieve higher classification accuracy than state-of-the-art algorithms.

Existing 3D human pose estimation (3D-HPE) methods focus on reducing the overall joint error, resulting in endpoints and bone lengths with large errors. To address this issue, we propose a human structure-aware network, which is capable of recovering 3D joint locations from given 2D joint detections. We cascade a refinement network with a basic network in a residual learning manner, meanwhile fuse the features from 2D and 3D coordinates by a residual connection. Specifically, our refinement network employs a dual-channel structure, in which the symmetrical endpoints are divided into two parts and refined separately. Such a structure is able to avoid the mutual interference of joints with large errors to promise reliable 3D features. Experimental results on the Human3.6M dataset demonstrate that our network reduces the errors of both endpoints and bone lengths compared with existing state-of-the-art approaches.

In this paper, we propose a new framework for hyperspectral image classification, namely pseudolabel guided kernel learning (PLKL). The proposed framework is capable of fully utilizing unlabeled samples, making it very effective to handle the task with extremely limited training samples. Specifically, with multiple initial kernels and labeled samples, we first employ support vector machine (SVM) classifiers to predict pseudolabels independently for each unlabeled sample, and consistency voting is applied to the resulting pseudolabels to select and add a few unlabeled samples to the training set. Then, we refine the kernels to improve their discriminability with the augmented training set and a typical kernel learning method. Such phases are repeated until stable. Furthermore, we enhance the PLKL in terms of both the computation and memory efficiencies by using a bagging-like strategy, improving its practicality for large scale datasets. In addition, the proposed framework is quite flexible and general. That is, other advanced kernel-based methods can be incorporated to continuously improve the performance. Experimental results show that the proposed frameworks achieve much higher classification accuracy, compared with state-of-the-art methods. Especially, the classification accuracy improves more than 5% with very few training samples.

Immersive learning in Virtual Reality (VR) environments is the developing trend for future education systems including remote physical training. This paper presents “ImmerTai”, a system that is designed for effective remote motion training, particularly for Chinese Taichi, in an immersive way. With ImmerTai, the Taichi expert’s motion is captured and delivered to remote students in CAVE, HMD and PC environments for learning. The students’ motions are also captured for motion quality assessment and a group of students can form a virtual collaborative learning scenario. We built up a Taichi motion dataset with ground truth of motion quality, and based on this, we developed and evaluated several motion quality assessment methods. Then, user tests were designed and carried out to measure and compare the learning outcomes (learning time, quality and overall efficiency) of students in Cave Automatic Virtual Environment (CAVE), Head Mounted Display (HMD) and Personal Computer (PC) environments. Meanwhile, the connections between students’ learning outcomes and their VR experience were investigated and discussed too. Our results show that ImmerTai can accelerate the learning process of students noticeably (up to 17%) compared to non-immersive learning with the conventional PC setup. However, we observed a substantial difference in the quality of the learnt motion between CAVE (26% gain) and HMD (23% drop) compared to PC (baseline). While strong VR presence can enhance the learning experience of students, their learning outcomes are not fully consistent to their experience. Overall, ImmerTai with CAVE demonstrated a significantly higher learning efficiency than other tested environments. This work was supported in part by the National Key Research and Development Program of China under Grant No. 2016YFC0801001, the National Program on Key Basic Research Projects (973 Program) under Grant 2015CB351803, NSFC under Grant 61571413, 61632001, 61390514, and Scientific and Technological Project Grant offered by the Ministry of Human Resources and Social Security of China and the Department of Human Resources and Social Security of Anhui Province, China.

In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the center points and sizes of crowded objects. Specifically, during training, we utilize the available point annotations to supervise the estimation of the center points of objects directly. Based on a locally-uniform distribution assumption, we initialize pseudo object sizes from the point-level supervisory information, which are then leveraged to guide the regression of object sizes via a crowdedness-aware loss. Meanwhile, we propose a confidence and order-aware refinement scheme to continuously refine the initial pseudo object sizes such that the ability of the detector is increasingly boosted to detect and count objects in crowds simultaneously. Moreover, to address extremely crowded scenes, we propose an effective decoding method to improve the detector's representation ability. Experimental results on the WiderFace benchmark show that our approach significantly outperforms state-of-the-art point-supervised methods under both detection and counting tasks, i.e., our method improves the average precision by more than 10% and reduces the counting error by 31.2%. Besides, our method obtains the best results on the crowd counting and localization datasets (i.e., ShanghaiTech and NWPU-Crowd) and vehicle counting datasets (i.e., CARPK and PUCPR+) compared with state-of-the-art counting-by-detection methods. The code will be publicly available at https://github.com/WangyiNTU/Point-supervised-crowd-detection., 12 pages. Accepted for Publication at IEEE Transactions on Image Processing

This paper explores the problem of reconstructing high-resolution light field (LF) images from hybrid lenses, including a high-resolution camera surrounded by multiple low-resolution cameras. To tackle this challenge, we propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input from two complementary and parallel perspectives. Specifically, one module regresses a spatially consistent intermediate estimation by learning a deep multidimensional and cross-domain feature representation; the other one constructs another intermediate estimation, which maintains the high-frequency textures, by propagating the information of the high-resolution view. We finally leverage the advantages of the two intermediate estimations via the learned attention maps, leading to the final high-resolution LF image. Extensive experiments demonstrate the significant superiority of our approach over state-of-the-art ones. That is, our method not only improves the PSNR by more than 2 dB, but also preserves the LF structure much better. To the best of our knowledge, this is the first end-to-end deep learning method for reconstructing a high-resolution LF image with a hybrid input. We believe our framework could potentially decrease the cost of high-resolution LF data acquisition and also be beneficial to LF data storage and transmission. The code is available at https://github.com/jingjin25/LFhybridSR-Fusion., This paper was accepted by ACM MM 2020

In this paper, we propose a deep learning based framework for point cloud geometry lossy compression via hybrid representation of point cloud. First, the input raw 3D point cloud data is adaptively decomposed into non-overlapping local patches through adaptive Octree decomposition and clustering. Second, a framework of point cloud auto-encoder network with quantization layer is proposed for learning compact latent feature representation from each patch. Specifically, the proposed point cloud auto-encoder networks with different input size are trained for achieving optimal rate-distortion (RD) performance. Final, bitstream specifications of proposed compression systems with additional signaled meta-data and header information are designed to support parallel decoding and successive reconstruction. Experimental results shows that our proposed method can achieve 40.20% bitrate saving in average than the existing standard Geometry based Point Cloud Compression (G-PCC) codec.

The light field captures both the spatial and angular configurations of the scene, which facilitates a wide range of imaging possibilities. In this work, we propose an LF view extrapolation algorithm which renders high quality novel LF views far outside the range of given angular baselines. A stratified synthesis strategy is adopted which projects the scene content based on stratified disparity layers and across varying scales of spatial granularities. Such a stratified methodology proves to help preserve scene structures over large angular shifts, and provide informative clues for inferring the contents of occluded regions. A generative-adversarial network model is further adopted for parallax correction and occlusion completion conditioned on surface consistent feature. Experiments show that our proposed model can provide more reliable novel view extrapolation quality at large baseline extension ratios compared with state-of-the-art LF synthesis algorithms.

Depth estimation is a fundamental problem for light field based applications. Although recent learning-based methods have proven to be effective for light field depth estimation, they still have troubles when handling occlusion regions. In this paper, by leveraging the explicitly learned occlusion map, we propose an occlusion-aware network, which is capable of estimating accurate depth maps with sharp edges. Our main idea is to separate the depth estimation on non-occlusion and occlusion regions, as they contain different properties with respect to the light field structure, i.e., obeying and violating the angular photo consistency constraint. To this end, three modules are involved in our network: the occlusion region detection network (ORDNet), the coarse depth estimation network (CDENet), and the refined depth estimation network (RDENet). Specifically, ORDNet predicts the occlusion map as a mask, while under the guidance of the resulting occlusion map, CDENet and REDNet focus on the depth estimation on non-occlusion and occlusion areas, respectively. Experimental results show that our method achieves better performance on 4D light field benchmark, especially in occlusion regions, when compared with current state-of-the-art light-field depth estimation algorithms.

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension. LF spatial super-resolution (SR) thus becomes an indispensable part of the LF camera processing pipeline. The high-dimensionality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. The performance of existing methods is still limited as they fail to thoroughly explore the coherence among LF views and are insufficient in accurately preserving the parallax structure of the scene. In this paper, we propose a novel learning-based LF spatial SR framework, in which each view of an LF image is first individually super-resolved by exploring the complementary information among views with combinatorial geometry embedding. For accurate preservation of the parallax structure among the reconstructed views, a regularization network trained over a structure-aware loss function is subsequently appended to enforce correct parallax relationships over the intermediate estimation. Our proposed approach is evaluated over datasets with a large number of testing images including both synthetic and real-world scenes. Experimental results demonstrate the advantage of our approach over state-of-the-art methods, i.e., our method not only improves the average PSNR by more than 1.0 dB but also preserves more accurate parallax details, at a lower computational cost., This paper was accepted by CVPR 2020

As a variant of non-negative matrix factorization (NMF), symmetric NMF (SymNMF) can generate the clustering result without additional post-processing, by decomposing a similarity matrix into the product of a clustering indicator matrix and its transpose. However, the similarity matrix in the traditional SymNMF methods is usually predefined, resulting in limited clustering performance. Considering that the quality of the similarity graph is crucial to the final clustering performance, we propose a new semisupervised model, which is able to simultaneously learn the similarity matrix with supervisory information and generate the clustering results, such that the mutual enhancement effect of the two tasks can produce better clustering performance. Our model fully utilizes the supervisory information in the form of pairwise constraints to propagate it for obtaining an informative similarity matrix. The proposed model is finally formulated as a non-negativity-constrained optimization problem. Also, we propose an iterative method to solve it with the convergence theoretically proven. Extensive experiments validate the superiority of the proposed model when compared with nine state-of-the-art NMF models.

Pairwise constraints (PCs) composed of must-links (MLs) and cannot-links (CLs) are widely used in many semisupervised tasks. Due to the limited number of PCs, pairwise constraint propagation (PCP) has been proposed to augment them. However, the existing PCP algorithms only adopt a single matrix to contain all the information, which overlooks the differences between the two types of links such that the discriminability of the propagated PCs is compromised. To this end, this article proposes a novel PCP model via dual adversarial manifold regularization to fully explore the potential of the limited initial PCs. Specifically, we propagate MLs and CLs with two separated variables, called similarity and dissimilarity matrices, under the guidance of the graph structure constructed from data samples. At the same time, the adversarial relationship between the two matrices is taken into consideration. The proposed model is formulated as a nonnegative constrained minimization problem, which can be efficiently solved with convergence theoretically guaranteed. We conduct extensive experiments to evaluate the proposed model, including propagation effectiveness and applications on constrained clustering and metric learning, all of which validate the superior performance of our model to state-of-the-art PCP models.

Salient object detection from RGB-D images is an important yet challenging vision task, which aims at detecting the most distinctive objects in a scene by combining color information and depth constraints. Unlike prior fusion manners, we propose an attention steered interweave fusion network (ASIF-Net) to detect salient objects, which progressively integrates cross-modal and cross-level complementarity from the RGB image and corresponding depth map via steering of an attention mechanism. Specifically, the complementary features from RGB-D images are jointly extracted and hierarchically fused in a dense and interweaved manner. Such a manner breaks down the barriers of inconsistency existing in the cross-modal data and also sufficiently captures the complementarity. Meanwhile, an attention mechanism is introduced to locate the potential salient regions in an attention-weighted fashion, which advances in highlighting the salient objects and suppressing the cluttered background regions. Instead of focusing only on pixelwise saliency, we also ensure that the detected salient objects have the objectness characteristics (e.g., complete structure and sharp boundary) by incorporating the adversarial learning that provides a global semantic constraint for RGB-D salient object detection. Quantitative and qualitative experiments demonstrate that the proposed method performs favorably against 17 state-of-the-art saliency detectors on four publicly available RGB-D salient object detection datasets. The code and results of our method are available at https://github.com/Li-Chongyi/ASIF-Net .

This paper explores the problem of hyperspectral image (HSI) super-resolution that merges a low resolution HSI (LR-HSI) and a high resolution multispectral image (HR-MSI). The cross-modality distribution of the spatial and spectral information makes the problem challenging. Inspired by the classic wavelet decomposition-based image fusion, we propose a novel \textit{lightweight} deep neural network-based framework, namely progressive zero-centric residual network (PZRes-Net), to address this problem efficiently and effectively. Specifically, PZRes-Net learns a high resolution and \textit{zero-centric} residual image, which contains high-frequency spatial details of the scene across all spectral bands, from both inputs in a progressive fashion along the spectral dimension. And the resulting residual image is then superimposed onto the up-sampled LR-HSI in a \textit{mean-value invariant} manner, leading to a coarse HR-HSI, which is further refined by exploring the coherence across all spectral bands simultaneously. To learn the residual image efficiently and effectively, we employ spectral-spatial separable convolution with dense connections. In addition, we propose zero-mean normalization implemented on the feature maps of each layer to realize the zero-mean characteristic of the residual image. Extensive experiments over both real and synthetic benchmark datasets demonstrate that our PZRes-Net outperforms state-of-the-art methods to a \textit{significant} extent in terms of both 4 quantitative metrics and visual quality, e.g., our PZRes-Net improves the PSNR more than 3dB, while saving 2.3$\times$ parameters and consuming 15$\times$ less FLOPs. The code is publicly available at https://github.com/zbzhzhy/PZRes-Net .

The acquisition of light field images with high angular resolution is costly. Although many methods have been proposed to improve the angular resolution of a sparsely-sampled light field, they always focus on the light field with a small baseline, which is captured by a consumer light field camera. By making full use of the intrinsic \textit{geometry} information of light fields, in this paper we propose an end-to-end learning-based approach aiming at angularly super-resolving a sparsely-sampled light field with a large baseline. Our model consists of two learnable modules and a physically-based module. Specifically, it includes a depth estimation module for explicitly modeling the scene geometry, a physically-based warping for novel views synthesis, and a light field blending module specifically designed for light field reconstruction. Moreover, we introduce a novel loss function to promote the preservation of the light field parallax structure. Experimental results over various light field datasets including large baseline light field images demonstrate the significant superiority of our method when compared with state-of-the-art ones, i.e., our method improves the PSNR of the second best method up to 2 dB in average, while saves the execution time 48$\times$. In addition, our method preserves the light field parallax structure better., Comment: This paper was accepted by AAAI 2020

Rate distortion optimization plays a very important role in image/video coding. But for 3D point cloud, this problem has not been investigated. In this paper, the rate and distortion characteristics of 3D point cloud are investigated in detail, and a typical and challenging rate distortion optimization problem is solved for 3D point cloud. Specifically, since the quality of the reconstructed 3D point cloud depends on both the geometry and color distortions, we first propose analytical rate and distortion models for the geometry and color information in video-based 3D point cloud compression platform, and then solve the joint bit allocation problem for geometry and color based on the derived models. To maximize the reconstructed quality of 3D point cloud, the bit allocation problem is formulated as a constrained optimization problem and solved by an interior point method. Experimental results show that the rate-distortion performance of the proposed solution is close to that obtained with exhaustive search but at only 0.68% of its time complexity. Moreover, the proposed rate and distortion models can also be used for the other rate-distortion optimization problems (such as prediction mode decision) and rate control technologies for 3D point cloud coding in the future., Comment: 13pages, 10 figures, submitted to IEEE Transactions on Multimedia

Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms. The bottleneck lies in the reconstruction algorithms, resulting in rather limited reconstruction quality. To tackle this challenge, we propose a novel learning-based framework for the reconstruction of high-quality LFs from acquisitions via learned coded apertures. The proposed method incorporates the measurement observation into the deep learning framework elegantly to avoid relying entirely on data-driven priors for LF reconstruction. Specifically, we first formulate the compressive LF reconstruction as an inverse problem with an implicit regularization term. Then, we construct the regularization term with an efficient deep spatial-angular convolutional sub-network to comprehensively explore the signal distribution free from the limited representation ability and inefficiency of deterministic mathematical modeling. Experimental results show that the reconstructed LFs not only achieve much higher PSNR/SSIM but also preserve the LF parallax structure better, compared with state-of-the-art methods on both real and synthetic LF benchmarks. In addition, experiments show that our method is efficient and robust to noise, which is an essential advantage for a real camera system. The code is publicly available at https://github.com/angmt2008/LFCA.

The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method trains a lightweight deep network, DCE-Net, to estimate pixel-wise and high-order curves for dynamic range adjustment of a given image. The curve estimation is specially designed, considering pixel value range, monotonicity, and differentiability. Zero-DCE is appealing in its relaxed assumption on reference images, i.e., it does not require any paired or unpaired data during training. This is achieved through a set of carefully formulated non-reference loss functions, which implicitly measure the enhancement quality and drive the learning of the network. Our method is efficient as image enhancement can be achieved by an intuitive and simple nonlinear curve mapping. Despite its simplicity, we show that it generalizes well to diverse lighting conditions. Extensive experiments on various benchmarks demonstrate the advantages of our method over state-of-the-art methods qualitatively and quantitatively. Furthermore, the potential benefits of our Zero-DCE to face detection in the dark are discussed. Code and model will be available at https://github.com/Li-Chongyi/Zero-DCE., Comment: 10 pages

As a variant of nonnegative matrix factorization (NMF), symmetric NMF (SNMF) has shown to be effective for capturing the cluster structure embedded in the graph representation. In contrast to the existing SNMF-based clustering methods that empirically construct the similarity matrix and rigidly introduce the supervisory information to the assignment matrix, in this paper, we propose a novel SNMF-based semisupervised clustering method, namely, pairwise constraint propagation-induced SNMF (PCPSNMF). By formulating a single-constrained optimization problem, PCPSNMF is capable of learning the similarity and assignment matrices adaptively and simultaneously , in which a small amount of supervisory information in the form of pairwise constraints is introduced in a flexible way to guide the construction of the similarity matrix, and the two matrices communicate with each other to achieve mutual refinement until convergence. In addition, we propose an efficient alternating iterative algorithm to solve the optimization problem, whose convergence is theoretically proven. Experimental results over several benchmark image data sets demonstrate that PCPSNMF is less sensitive to initialization and produces higher clustering performance, compared with the state-of-the-art methods.

Depth estimation is a fundamental problem for light field photography applications. Numerous methods have been proposed in recent years, which either focus on crafting cost terms for more robust matching, or on analyzing the geometry of scene structures embedded in the epipolar-plane images. Significant improvements have been made in terms of overall depth estimation error; however, current state-of-the-art methods still show limitations in handling intricate occluding structures and complex scenes with multiple occlusions. To address these challenging issues, we propose a very effective depth estimation framework which focuses on regularizing the initial label confidence map and edge strength weights. Specifically, we first detect partially occluded boundary regions (POBR) via superpixel-based regularization. Series of shrinkage/reinforcement operations are then applied on the label confidence map and edge strength weights over the POBR. We show that after weight manipulations, even a low-complexity weighted least squares model can produce much better depth estimation than the state-of-the-art methods in terms of average disparity error rate, occlusion boundary precision-recall rate, and the preservation of intricate visual features. NRF (Natl Research Foundation, S’pore)

Light field (LF) cameras provide perspective information of scenes by taking directional measurements of the focusing light rays. The raw outputs are usually dark with additive camera noise, which impedes subsequent processing and applications. We propose a novel LF denoising framework based on anisotropic parallax analysis (APA). Two convolutional neural networks are jointly designed for the task: first, the structural parallax synthesis network predicts the parallax details for the entire LF based on a set of anisotropic parallax features. These novel features can efficiently capture the high-frequency perspective components of a LF from noisy observations. Second, the view-dependent detail compensation network restores non-Lambertian variation to each LF view by involving view-specific spatial energies. Extensive experiments show that the proposed APA LF denoiser provides a much better denoising performance than state-of-the-art methods in terms of visual quality and in preservation of parallax details. NRF (Natl Research Foundation, S’pore)

Arising from various environmental and atmos- pheric conditions and sensor interference, spectral variations are inevitable during hyperspectral remote sensing, which degrade the subsequent hyperspectral image analysis significantly. In this paper, we propose simultaneous spatial and spectral low-rank representation (S3LRR) that can effectively suppress the within-class spectral variations for classification purposes. The S3LRR recovers an intrinsic component with the same dimension as the original image, in which both spatial and spectral low-rank priors are adopted to regularize the intrinsic component simultaneously and compensate to each other, together with robust modeling of spectral variations. Compared with existing methods that explore only the spectral low-rank prior, the novel spatial low-rank prior (i.e., low-rank prior in band-wise) can take the spatial structure information of hyperspectral images into account, which has demonstrated to be very useful. Technically, we formulate S3LRR as a constrained convex optimization problem, and solve it using the efficient inexact augmented Lagrangian multiplier method. The resulting intrinsic component is less interfered by within-class spectral variations, and more discriminatory to offer higher classification accuracy. Comprehensive experiments on benchmark data sets demonstrate that the proposed S3LRR improves classification accuracy significantly, which outperforms state-of-the-art methods.

Spectral clustering (SC) is one of the most widely used clustering methods. In this letter, we extend the traditional SC with a semi-supervised manner. Specifically, with the guidance of small amount of supervisory information, we build a matrix with anti-block-diagonal appearance, which is further utilized to regularize the product of the low-dimensional embedding and its transpose. Technically, we formulate the proposed model as a constrained optimization problem. Then, we relax it as a convex problem, which can be efficiently solved with the global convergence guaranteed via the inexact augmented Lagrangian multiplier method. Experimental results over four real-world datasets demonstrate that higher accuracy and normalized mutual information are achieved when compared with state-of-the-art methods.

Convolutional neural network (CNN) is well known for its capability of feature learning and has made revolutionary achievements in many applications, such as scene recognition and target detection. In this paper, its capability of feature learning in hyperspectral images is explored by constructing a five-layer CNN for classification (C-CNN). The proposed C-CNN is constructed by including recent advances in deep learning area, such as batch normalization, dropout, and parametric rectified linear unit (PReLU) activation function. In addition, both spatial context and spectral information are elegantly integrated into the C-CNN such that spatial-spectral features are learned for hyperspectral images. A companion feature-learning CNN (FL-CNN) is constructed by extracting fully connected feature layers in this C-CNN. Both supervised and unsupervised modes are designed for the proposed FL-CNN to learn sensor-specific spatial-spectral features. Extensive experimental results on four benchmark data sets from two well-known hyperspectral sensors, namely airborne visible/infrared imaging spectrometer (AVIRIS) and reflective optics system imaging spectrometer (ROSIS) sensors, demonstrate that our proposed C-CNN outperforms the state-of-the-art CNN-based classification methods, and its corresponding FL-CNN is very effective to extract sensor-specific spatial-spectral features for hyperspectral applications under both supervised and unsupervised modes.

Within-class spectral variation, which is caused by varied imaging conditions, such as changes in illumination, environmental, atmospheric, and temporal conditions, significantly degrades the performance of hyperspectral image classification. Recent studies have shown that such spectral variation can be alleviated by exploring the low-rank property in the spectral domain, especially based on the low-rank subspace assumption. In this paper, the low-rank subspace assumption is approached by exploring the low-rank property in the local spectral domain. In addition, the low-rank property in the spatial domain is also explored to alleviate spectral variation. As a result, two novel spectral-spatial low-rank (SSLR) strategies are designed to alleviate spectral variation by exploring the low-rank property in both spectral and spatial domains. Experimental results on two benchmark hyperspectral datasets demonstrate that exploring the low-rank property in local spectral space can help to alleviate spectral variation and improve the performance of classification obviously for all tested data, while exploring the low-rank property in spatial space is more effective for images presenting large homogeneous areas.

Dynamic Adaptive Streaming over HTTP (DASH) has demonstrated to be an emerging and promising multimedia streaming technique, owing to its capability of dealing with the variability of networks. Rate adaptation mechanism, a challenging and open issue, plays an important role in DASH based systems since it affects Quality of Experience (QoE) of users, network utilization, etc. In this paper, based on non-cooperative game theory, we propose a novel algorithm to optimally allocate the limited export bandwidth of the server to multi-users to maximize their QoE with fairness guaranteed. The proposed algorithm is proxy-free. Specifically, a novel user QoE model is derived by taking a variety of factors into account, like the received video quality, the reference buffer length, and user accumulated buffer lengths, etc. Then, the bandwidth competing problem is formulated as a non-cooperation game with the existence of Nash Equilibrium that is theoretically proven. Finally, a distributed iterative algorithm with stability analysis is proposed to find the Nash Equilibrium. Compared with state-of-the-art methods, extensive experimental results in terms of both simulated and realistic networking scenarios demonstrate that the proposed algorithm can produce higher QoE, and the actual buffer lengths of all users keep nearly optimal states, i.e., moving around the reference buffer all the time. Besides, the proposed algorithm produces no playback interruption., This paper has been published on IEEE Transactions on Mobile Computing. H. Yuan, H. Fu, J. Liu, J. Hou, and S. Kwong, "Non-Cooperative Game Theory Based Rate Adaptation for Dynamic Video Streaming over HTTP," IEEE Transactions on Mobile Computing, vol.17, no.10, pp. 2334-2348, Oct. 2018

Pairwise constraint propagation (PCP) aims to propagate a limited number of initial pairwise constraints (PCs, including must-link and cannot-link constraints) from the constrained data samples to the unconstrained ones to boost subsequent PC-based applications. The existing PCP approaches always suffer from the imbalance characteristic of PCs, which limits their performance significantly. To this end, we propose a novel imbalance-aware PCP method, by comprehensively and theoretically exploring the intrinsic structures of the underlying PCs. Specifically, different from the existing methods that adopt a single representation, we propose to use two separate carriers to represent the two types of links. And the propagation is driven by the structure embedded in data samples and the regularization of the local, global, and complementary structures of the two carries. Our method is elegantly cast as a well-posed constrained optimization model, which can be efficiently solved. Experimental results demonstrate that the proposed PCP method is capable of generating more high-fidelity PCs than the recent PCP algorithms. In addition, the augmented PCs by our method produce higher accuracy than state-of-the-art semi-supervised clustering methods when applied to constrained clustering. To the best of our knowledge, this is the first PCP method taking the imbalance property of PCs into account.

Regularization is commonly used for alleviating overfitting in machine learning. For convolutional neural networks (CNNs), regularization methods, such as DropBlock and Shake-Shake, have illustrated the improvement in the generalization performance. However, these methods lack a self-adaptive ability throughout training. That is, the regularization strength is fixed to a predefined schedule, and manual adjustments are required to adapt to various network architectures. In this paper, we propose a dynamic regularization method for CNNs. Specifically, we model the regularization strength as a function of the training loss. According to the change of the training loss, our method can dynamically adjust the regularization strength in the training procedure, thereby balancing the underfitting and overfitting of CNNs. With dynamic regularization, a large-scale model is automatically regularized by the strong perturbation, and vice versa. Experimental results show that the proposed method can improve the generalization capability on off-the-shelf network architectures and outperform state-of-the-art regularization methods., 7 pages. Accepted for Publication at IEEE TNNLS

In this article, we propose a semi-supervised non-negative matrix factorization (NMF) model by means of elegantly modeling the label information. The proposed model is capable of generating discriminable low-dimensional representations to improve clustering performance. Specifically, a pair of complementary regularizers, i.e., similarity and dissimilarity regularizers, is incorporated into the conventional NMF to guide the factorization. And, they impose restrictions on both the similarity and dissimilarity of the low-dimensional representations of data samples with labels as well as a small number of unlabeled ones. The proposed model is formulated as a well-posed constrained optimization problem and further solved with an efficient alternating iterative algorithm. Moreover, we theoretically prove that the proposed algorithm can converge to a limiting point that meets the Karush–Kuhn–Tucker conditions. Extensive experiments as well as comprehensive analysis demonstrate that the proposed model outperforms the state-of-the-art NMF methods to a large extent over five benchmark data sets, i.e., the clustering accuracy increases to 82.2% from 57.0%.

In this paper, we present an effective convolutional neural network (CNN) for object counting in video surveillance, namely multi-scale density map regressor (MSDMR). In contrast to existing CNN-based methods that achieve high accuracy by means of empirically increasing the model capacity with more complex structures/layers, we focus on a compact CNN. Specifically, the MSDMR is mainly designed with the supervision of multi-scale outputs, in which two CNN stacks estimate coarse- and fine-scale density maps, respectively. The integral of the fine density map provides the count of objects. The two stacks are connected in a cascaded manner and jointly trained such that the overall model can learn discriminative and complementary features to produce expressive performance. Experimental results show that the proposed MSDMR can achieve higher accuracy compared with state-of-the-art methods on the surveillance datasets.

Graph-based clustering methods have demonstrated the effectiveness in various applications. Generally, existing graph-based clustering methods first construct a graph to represent the input data and then partition it to generate the clustering result. However, such a stepwise manner may make the constructed graph not fit the requirements for the subsequent decomposition, leading to compromised clustering accuracy. To this end, we propose a joint learning framework, which is able to learn the graph and the clustering result simultaneously, such that the resulting graph is tailored to the clustering task. The proposed method is formulated as a well-defined nonnegative and off-diagonal constrained optimization problem,which is optimized by an alternative iteration method with the convergence of the value of the objective function guaranteed. The advantage of the proposed model is demonstrated by comparing with 19 state-of-the-art clustering methods on 10 datasets with 4 clustering metrics.

Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image enhancement algorithms have been proposed in the last few years. However, these algorithms are mainly evaluated using either synthetic datasets or few selected real-world images. It is thus unclear how these algorithms would perform on images acquired in the wild and how we could gauge the progress in the field. To bridge this gap, we present the first comprehensive perceptual study and analysis of underwater image enhancement using large-scale real-world images. In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images. We treat the rest 60 underwater images which cannot obtain satisfactory reference images as challenging data. Using this dataset, we conduct a comprehensive study of the state-of-the-art underwater image enhancement algorithms qualitatively and quantitatively. In addition, we propose an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs). The benchmark evaluations and the proposed Water-Net demonstrate the performance and limitations of state-of-the-art algorithms, which shed light on future research in underwater image enhancement. The dataset and code are available at https://li-chongyi.github.io/proj_benchmark.html., Comment: 14 pages

Spectral variation is profound in remotely sensed images due to variable imaging conditions. The wide presence of such spectral variation degrades the performance of hyperspectral analysis, such as classification and spectral unmixing. In this letter, $\ell_{1}$ -based low-rank matrix approximation is proposed to alleviate spectral variation for hyperspectral image analysis. Specifically, hyperspectral image data are decomposed into a low-rank matrix and a sparse matrix, and it is assumed that intrinsic spectral features are represented by the low-rank matrix and spectral variation is accommodated by the sparse matrix. As a result, the performance of image data analysis can be improved by working on the low-rank matrix. Experiments on benchmark hyperspectral data sets demonstrate the performance of classification, and spectral unmixing can be clearly improved by the proposed approach.

A human-computer interface (namely Facial position and expression Mouse system, FM) for the persons with tetraplegia based on a monocular infrared depth camera is presented in this paper. The nose position along with the mouth status (close/open) is detected by the proposed algorithm to control and navigate the cursor as computer user input. The algorithm is based on an improved Randomized Decision Tree, which is capable of detecting the facial information efficiently and accurately. A more comfortable user experience is achieved by mapping the nose motion to the cursor motion via a nonlinear function. The infrared depth camera enables the system to be independent of illumination and color changes both from the background and on human face, which is a critical advantage over RGB camera-based options. Extensive experimental results show that the proposed system outperforms existing assistive technologies in terms of quantitative and qualitative assessments.

Head pose estimation plays a vital role in various applications, e.g., driver-assistance systems, human-computer interaction, virtual reality technology, and so on. We propose a novel geometry-based method for accurately estimating the head pose from a single 2D face image at a very low computational cost. Specifically, the rectangular coordinates of only four non-coplanar feature points from a predefined 3D facial model as well as the corresponding ones automatically/manually extracted from a 2D face image are first normalized to exclude the effect of external factors (i.e., scale factor and translation parameters). Then, the four normalized 3D feature points are represented in spherical coordinates with reference to the uniquely determined sphere by themselves. Due to the spherical parametrization, the coordinates of feature points can then be morphed along all the three directions in the rectangular coordinates effectively. Finally, the rotation matrix indicating the head pose is obtained by minimizing the Euclidean distance between the normalized 2D feature points and the 2D re-projections of the morphed 3D feature points. Comprehensive experimental results over two popular datasets, i.e., Pointing’04 and Biwi Kinect, demonstrate that the proposed method can estimate head poses with higher accuracy and lower run time than state-of-the-art geometry-based methods. Even compared with start-of-the-art learning-based methods or geometry-based methods with additional depth information, our method still produces comparable performance.

Light field (LF) photography is an emerging paradigm for capturing more immersive representations of the real-world. However, arising from the inherent trade-off between the angular and spatial dimensions, the spatial resolution of LF images captured by commercial micro-lens based LF cameras are significantly constrained. In this paper, we propose effective and efficient end-to-end convolutional neural network models for spatially super-resolving LF images. Specifically, the proposed models have an hourglass shape, which allows feature extraction to be performed at the low resolution level to save both computational and memory costs. To fully make use of the four-dimensional (4-D) structure information of LF data in both spatial and angular domains, we propose to use 4-D convolution to characterize the relationship among pixels. Moreover, as an approximation of 4-D convolution, we also propose to use spatialangular separable (SAS) convolutions for more computationallyand memory-efficient extraction of spatial-angular joint features. Extensive experimental results on 57 test LF images with various challenging natural scenes show significant advantages from the proposed models over state-of-the-art methods. That is, an average PSNR gain of more than 3.0 dB and better visual quality are achieved, and our methods preserve the LF structure of the super-resolved LF images better, which is highly desirable for subsequent applications. In addition, the SAS convolutionbased model can achieve 3× speed up with only negligible reconstruction quality decrease when compared with the 4-D convolution-based one. The source code of our method is online available at https://github.com/spatialsr/DeepLightFieldSSR.

Light field (LF) has proven to be promising in immersive representation of the real world. However, a major limitation of micro-lens array based LF camera is the low spatial resolution, due to the inherent trade-off between angular and spatial dimensions. In this paper, we propose a framework to show that a single high-resolution (HR) RGB image effectively improves the performance of LF spatial super-resolution. We adopt an end-to-end convolutional neural network, which takes a low-resolution (LR) light field image (LFI) and a single HR center view as inputs. The LFI provides the information about LF structure in angular domain, while the HR center view provides more details in spatial domain. Experimental results on 57 test LFIs with various challenging natural scenes demonstrate that our algorithm outperforms current state-of-the-art methods.

Light field, as a popular representation of three-dimensional scenes, attracted much attention in the research community recently. For light field images, various processing operations might degrade the image quality. In this work, we propose a visual quality assessment method for light field images (LFIs) based on local and global features of epipolar plane images (EPIs). It is known that EPI reflects the relationship among LFIs in both 2D spatial domain (x, y) and angular domain (s, t). We use gradient magnitude similarity to compute the local visual quality variations of LFIs. Additionally, the global structure features are extracted to predict the global variations for LFIs. The final quality score of LFIs is calculated by combining the local and global variations. Experimental results show that the proposed method can obtain consistent results of visual quality assessment for LFIs with human ratings

Rate-distortion optimal 3D point cloud compression is very challenging due to the irregular structure of 3D point clouds. For a popular 3D point cloud codec that uses octrees for geometry compression and JPEG for color compression, we first find analytical models that describe the relationship between the encoding parameters and the bitrate and distortion, respectively. We then use our models to formulate the rate-distortion optimization problem as a constrained convex optimization problem and apply an interior point method to solve it. Experimental results for six 3D point clouds show that our technique gives similar results to exhaustive search at only about 1.57% of its computational cost.

In this paper, we propose a new algorithm for constrained clustering, in which a new regularizer elegantly incorporates a small amount of weakly supervisory information in the form of pair-wise constraints to regularize the similarity between the low-dimensional representations of a set of data samples. By exploring both the local and global structures of the data samples with the guidance of the supervisory information, the proposed algorithm is capable of learning the low-dimensional representations with strong separability. Technically, the proposed algorithm is formulated and relaxed as a convex optimization model, which is further efficiently solved with the global convergence guaranteed. Experimental results on multiple benchmark data sets show that our proposed model can produce higher clustering accuracy than state-of-the-art algorithms.

Rain removal is important for improving the robustness of outdoor vision based systems. Current rain removal methods show limitations either for complex dynamic scenes shot from fast moving cameras, or under torrential rain fall with opaque occlusions. We propose a novel derain algorithm, which applies superpixel (SP) segmentation to decompose the scene into depth consistent units. Alignment of scene contents are done at the SP level, which proves to be robust towards rain occlusion and fast camera motion. Two alignment output tensors, i.e., optimal temporal match tensor and sorted spatial-temporal match tensor, provide informative clues for rain streak location and occluded background contents to generate an intermediate derain output. These tensors will be subsequently prepared as input features for a convolutional neural network to restore high frequency details to the intermediate output for compensation of mis-alignment blur. Extensive evaluations show that up to 5 dB reconstruction PSNR advantage is achieved over state-of-the-art methods. Visual inspection shows that much cleaner rain removal is achieved especially for highly dynamic scenes with heavy and opaque rainfall from a fast moving camera.