Search

JPEG, which was developed 30 years ago, is the most widely used image coding format, especially favored by the resource-deficient devices, due to its simplicity and efficiency. With the evolution of the Internet and the popularity of mobile devices, a huge amount of user-generated JPEG images are uploaded to social media sites like Facebook and Flickr or stored in personal computers or notebooks, which leads to an increase in storage cost. However, the performance of JPEG is far from the-state-of-the art coding methods. Therefore, the lossless recompression of JPEG images is urgent to be studied, which will further reduce the storage cost while maintaining the image fidelity. In this paper, a hybrid coding framework for the lossless recompression of JPEG images (LLJPEG) using transform domain intra prediction is proposed, including block partition and intraprediction, transform and quantization, and entropy coding. Specifically, in LLJPEG, intra prediction is first used to obtain a predicted block. Then the predicted block is transformed by DCT and then quantized to obtain the predicted coefficients. After that, the predicted coefficients are subtracted from the original coefficients to get the DCT coefficient residuals. Finally, the DCT residuals are entropy coded. In LLJPEG, some new coding tools are proposed for intra prediction and the entropy coding is redesigned. The experiments show that LLJPEG can reduce the storage space by 29.43% and 26.40% on the Kodak and DIV2K datasets respectively without any loss for JPEG images, while maintaining low decoding complexity. [ABSTRACT FROM AUTHOR]

Cross-modality face image synthesis such as sketch-to-photo, NIR-to-RGB, and RGB-to-depth has wide applications in face recognition, face animation, and digital entertainment. Conventional cross-modality synthesis methods usually require paired training data, i.e., each subject has images of both modalities. However, paired data can be difficult to acquire, while unpaired data commonly exist. In this paper, we propose a novel semi-supervised cross-modality synthesis method (namely CMOS-GAN), which can leverage both paired and unpaired face images to learn a robust cross-modality synthesis model. Specifically, CMOS-GAN uses a generator of encoder-decoder architecture for new modality synthesis. We leverage pixel-wise loss, adversarial loss, classification loss, and face feature loss to exploit the information from both paired multi-modality face images and unpaired face images for model learning. In addition, since we expect the synthetic new modality can also be helpful for improving face recognition accuracy, we further use a modified triplet loss to retain the discriminative features of the subject in the synthetic modality. Experiments on three cross-modality face synthesis tasks (NIR-to-VIS, RGB-to-depth, and sketch-to-photo) show the effectiveness of the proposed approach compared with the state-of-the-art. In addition, we also collect a large-scale RGB-D dataset (VIPL-MumoFace-3K) for the RGB-to-depth synthesis task. We plan to open-source our code and VIPL-MumoFace-3K dataset to the community (https://github.com/skgyu/CMOS-GAN). [ABSTRACT FROM AUTHOR]

Low-rank tensor representation philosophy has enjoyed a reputation in many hyperspectral image (HSI) low-level vision applications, but previous studies often failed to comprehensively exploit the low-rank nature of HSI along different modes in low-dimensional subspace, and unsurprisingly handled only one specific task. To address these challenges, in this paper, we figured out that in addition to the spatial correlation, the spectral dependency of HSI also implicitly exists in the coefficient tensor of its subspace, this crucial dependency that was not fully utilized by previous studies yet can be effectively exploited in a cascaded manner. This led us to propose a unified subspace low-rank learning regime with a new tensor cascaded rank minimization, named STCR, to fully couple the low-rankness of HSI in different domains for various low-level vision tasks. Technically, the high-dimensional HSI was first projected into a low-dimensional tensor subspace, then a novel tensor low-cascaded-rank decomposition was designed to collapse the constructed tensor into three core tensors in succession to more thoroughly exploit the correlations in spatial, nonlocal, and spectral modes of the coefficient tensor. Next, difference continuity-regularization was introduced to learn a basis that more closely approximates the HSI’s endmembers. The proposed regime realizes a comprehensive delineation of the self-portrait of HSI tensor. Extensive evaluations conducted with dozens of state-of-the-art (SOTA) baselines on eight datasets verified that the proposed regime is highly effective and robust to typical HSI low-level vision tasks, including denoising, compressive sensing reconstruction, inpainting, and destriping. The source code of our method is released at https://github.com/CX-He/STCR.git. [ABSTRACT FROM AUTHOR]

How to avoid biased predictions is an important and active research question in scene graph generation (SGG). Current state-of-the-art methods employ debiasing techniques such as resampling and causality analysis. However, the role of intrinsic cues in the features causing biased training has remained under-explored. In this paper, for the first time, we make the surprising observation that object identity information, in the form of object label embeddings (e.g. GLOVE), is principally responsible for biased predictions. We empirically observe that, even without any visual features, a number of recent SGG models can produce comparable or even better results solely from object label embeddings. Motivated by this insight, we propose to leverage a conditional variational auto-encoder to decouple the entangled visual features into two meaningful components: the object’s intrinsic identity features and the extrinsic, relation-dependent state feature. We further develop two compositional learning strategies on the relation and object levels to mitigate the data scarcity issue of rare relations. On the two benchmark datasets Visual Genome and GQA, we conduct extensive experiments on the three scenarios, i.e., conventional, few-shot and zero-shot SGG. Results consistently demonstrate that our proposed Decomposition and Composition (DeC) method effectively alleviates the biases in the relation prediction. Moreover, DeC is model-free, and it significantly improves the performance of recent SGG models, establishing new state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Grain size statistics, texture, and grain boundary distribution are microstructural characteristics that greatly influence materials properties. These characteristics can be derived from an orientation map obtained using orientation imaging microscopy (OIM) techniques. The OIM techniques are generally performed using a transmission electron microscopy (TEM) for nanomaterials. Although some of these techniques have limited applicability in certain situations, others have limited availability because of external hardware required. In this paper, an automated method to generate orientation maps using convergence beam electron diffraction patterns obtained in a conventional TEM setup is presented. This method is based upon dynamical diffraction theory that describes electron diffraction more accurately as compared with kinematical theory used by several existing OIM techniques. In addition, the method of this paper uses wide angle convergent beam electron diffraction for performing OIM. It is shown in this paper that the use of the wide angle convergent electron beam provides additional information that is not available otherwise. Together, the presented method exploits the additional information and combines it with the calculations from the dynamical theory to provide accurate orientation maps in a conventional TEM setup. The automated method of this paper is applied to a platinum thin film sample. The presented method correctly identified the texture preference in the sample. [ABSTRACT FROM PUBLISHER]

Recent advances in online visual tracking focus on designing part-based model to handle the deformation and occlusion challenges. However, previous methods usually consider only the pairwise structural dependences of target parts in two consecutive frames rather than the higher order constraints in multiple frames, making them less effective in handling large deformation and occlusion challenges. This paper describes a new and efficient method for online deformable object tracking. Different from most existing methods, this paper exploits higher order structural dependences of different parts of the tracking target in multiple consecutive frames. We construct a structure-aware hyper-graph to capture such higher order dependences, and solve the tracking problem by searching dense subgraphs on it. Furthermore, we also describe a new evaluating data set for online deformable object tracking (the Deform-SOT data set), which includes 50 challenging sequences with full annotations that represent realistic tracking challenges, such as large deformations and severe occlusions. The experimental result of the proposed method shows considerable improvement in performance over the state-of-the-art tracking methods. [ABSTRACT FROM PUBLISHER]

Contour completion plays an important role in visual perception, where the goal is to group fragmented low-level edge elements into perceptually coherent and salient contours. Most existing methods for contour completion have focused on pixelwise detection accuracy. In contrast, fewer methods have addressed the global contour closure effect, despite psychological evidences for its importance. This paper proposes a purely contour-based higher order CRF model to achieve contour closure, through local connectedness approximation. This leads to a simplified problem structure, where our higher order inference problem can be transformed into an integer linear program and be solved efficiently. Compared with the methods based on the same bottom–up edge detector, our method achieves a superior contour grouping ability (measured by Rand index), a comparable precision–recall performance, and more visually pleasing results. Our results suggest that contour closure can be effectively achieved in contour domain, in contrast to a popular view that segmentation is essential for this purpose. [ABSTRACT FROM PUBLISHER]

This paper presents an automatic method to extract a multi-view object in a natural environment. We assume that the target object is bounded by the convex volume of interest defined by the overlapping space of camera viewing frustums. There are two key contributions of our approach. First, we present an automatic method to identify a target object across different images for multi-view binary co-segmentation. The extracted target object shares the same geometric representation in space with a distinctive color and texture model from the background. Second, we present an algorithm to detect color ambiguous regions along the object boundary for matting refinement. Our matting region detection algorithm is based on the information theory, which measures the Kullback–Leibler divergence of local color distribution of different pixel bands. The local pixel band with the largest entropy is selected for matte refinement, subject to the multi-view consistent constraint. Our results are high-quality alpha mattes consistent across all different viewpoints. We demonstrate the effectiveness of the proposed method using various examples. [ABSTRACT FROM PUBLISHER]

This paper proposes a new method of calculating a matching metric for motion estimation. The proposed method splits the information in the source images into multiple scale and orientation subbands, reduces the subband values to a binary representation via an adaptive thresholding algorithm, and uses mutual information to model the similarity of corresponding square windows in each image. A moving window strategy is applied to recover a dense estimated motion field whose properties are explored. The proposed matching metric is a sum of mutual information scores across space, scale, and orientation. This facilitates the exploitation of information diversity in the source images. Experimental comparisons are performed amongst several related approaches, revealing that the proposed matching metric is better able to exploit information diversity, generating more accurate motion fields. [ABSTRACT FROM AUTHOR]

This paper presents algorithms for the digital restoration of films damaged by tear. As well as causing local image data loss, a tear results in a noticeable relative shift in the frame between the regions at either side of the tear boundary. This paper describes a method for delineating the tear boundary and for correcting the displacement. This is achieved using a graph-cut segmentation framework that can be either automatic or interactive when automatic segmentation is not possible. Using temporal intensity differences to form the boundary conditions for the segmentation facilitates the robust division of the frame. The resulting segmentation map is used to calculate and correct the relative displacement using a global-motion estimation approach based on motion histograms. A high-quality restoration is obtained when a suitable missing-data treatment algorithm is used to recover any missing pixel intensities. [ABSTRACT FROM AUTHOR]

Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue task involves multiple rounds of dialogues which cover a broad range of visual content that could be related to any objects, relationships or high-level semantics. Thus one of the key challenges in Visual Dialogue task is to learn a more comprehensive and semantic-rich image representation that can adaptively attend to the visual content referred by variant questions. In this paper, we first propose a novel scheme to depict an image from both visual and semantic views. Specifically, the visual view aims to capture the appearance-level information in an image, including objects and their visual relationships, while the semantic view enables the agent to understand high-level visual semantics from the whole image to the local regions. Furthermore, on top of such dual-view image representations, we propose a Dual Encoding Visual Dialogue (DualVD) module, which is able to adaptively select question-relevant information from the visual and semantic views in a hierarchical mode. To demonstrate the effectiveness of DualVD, we propose two novel visual dialogue models by applying it to the Late Fusion framework and Memory Network framework. The proposed models achieve state-of-the-art results on three benchmark datasets. A critical advantage of the DualVD module lies in its interpretability. We can analyze which modality (visual or semantic) has more contribution in answering the current question by explicitly visualizing the gate values. It gives us insights in understanding of information selection mode in the Visual Dialogue task. The code is available at https://github.com/JXZe/Learning_DualVD. [ABSTRACT FROM AUTHOR]

When imaging through a semi-reflective medium such as glass, the reflection of another scene can often be found in the captured images. It degrades the quality of the images and affects their subsequent analyses. In this paper, a novel deep neural network approach for solving the reflection problem in imaging is presented. Traditional reflection removal methods not only require long computation time for solving different optimization functions, their performance is also not guaranteed. As array cameras are readily available in nowadays imaging devices, we first suggest in this paper a multiple-image based depth estimation method using a convolutional neural network (CNN). The proposed network avoids the depth ambiguity problem due to the reflection in the image, and directly estimates the depths along the image edges. They are then used to classify the edges as belonging to the background or reflection. Since edges having similar depth values are error prone in the classification, they are removed from the reflection removal process. We suggest a generative adversarial network (GAN) to regenerate the removed background edges. Finally, the estimated background edge map is fed to another auto-encoder network to assist the extraction of the background from the original image. Experimental results show that the proposed reflection removal algorithm achieves superior performance both quantitatively and qualitatively as compared to the state-of-the-art methods. The proposed algorithm also shows much faster speed compared to the existing approaches using the traditional optimization methods. [ABSTRACT FROM AUTHOR]

Introduces image processing methods for electronic compensation of show-through. Show-through model and analysis; Description on the linearized show-through model; Show-through correction algorithm; Experimental results.

Identifying the underlying models in a set of data points that is contaminated by noise and outliers leads to a highly complex multi-model fitting problem. This problem can be posed as a clustering problem by the projection of higher-order affinities between data points into a graph, which can be clustered using spectral clustering. Calculating all possible higher-order affinities is computationally expensive. Hence, in most cases, only a subset is used. In this paper, we propose an effective sampling method for obtaining a highly accurate approximation of the full graph, which is required to solve multi-structural model fitting problems in computer vision. The proposed method is based on the observation that the usefulness of a graph for segmentation improves as the distribution of the hypotheses that are used to build the graph approaches the distribution of the actual parameters for the given data. In this paper, we approximate this actual parameter distribution by using a $k$ th-order statistics-based cost function, and the samples are generated using a greedy algorithm that is coupled with a data sub-sampling strategy. The experimental analysis shows that the proposed method is both accurate and computationally efficient compared with the state-of-the-art robust multi-model fitting techniques. The implementation of the method is publicly available from https://github.com/RuwanT/model-fitting-cbs. [ABSTRACT FROM AUTHOR]

Pansharpening is an important application in remote sensing image processing. It can increase the spatial-resolution of a multispectral image by fusing it with a high spatial-resolution panchromatic image in the same scene, which brings great favor for subsequent processing such as recognition, detection, etc. In this paper, we propose a continuous modeling and sparse optimization based method for the fusion of a panchromatic image and a multispectral image. The proposed model is mainly based on reproducing kernel Hilbert space (RKHS) and approximated Heaviside function (AHF). In addition, we also propose a Toeplitz sparse term for representing the correlation of adjacent bands. The model is convex and solved by the alternating direction method of multipliers which guarantees the convergence of the proposed method. Extensive experiments on many real datasets collected by different sensors demonstrate the effectiveness of the proposed technique as compared with several state-of-the-art pansharpening approaches. [ABSTRACT FROM AUTHOR]

Articulated hand pose estimation is one of core technologies in human–computer interaction. Despite the recent progress, most existing methods still cannot achieve satisfactory performance, partly due to the difficulty of the embedded high-dimensional nonlinear regression problem. Most existing data-driven methods directly regress 3D hand pose from 2D depth image, which cannot fully utilize the depth information. In this paper, we propose a novel multi-view convolutional neural network (CNN)-based approach for 3D hand pose estimation. To better exploit 3D information in the depth image, we project the point cloud generated from the query depth image onto multiple views of two projection settings and integrate them for more robust estimation. Multi-view CNNs are trained to learn the mapping from projected images to heat-maps, which reflect probability distributions of joints on each view. These multi-view heat-maps are then fused to estimate the optimal 3D hand pose with learned pose priors, and the unreliable information in multi-view heat-maps is suppressed using a view selection method. Experimental results show that the proposed method is superior to the state-of-the-art methods on two challenging data sets. Furthermore, a cross-data set experiment also validates that our proposed approach has good generalization ability. [ABSTRACT FROM AUTHOR]

Video object segmentation (VOS) is important for various computer vision problems, and handling it with minimal human supervision is highly desired for the large-scale applications. To bring down the supervision, existing approaches largely follow a data mining perspective by assuming the availability of multiple videos sharing the same object categories. It, however, would be problematic for the tasks that consume a single video. To address this problem, this paper proposes a novel approach that explores weakly labeled images to solve video object segmentation. Given a video labeled with a target category, images labeled with the same category are collected, from which noisy object exemplars are automatically discovered. After that the proposed approach extracts a set of region proposals on various frames and efficiently matches them with massive noisy exemplars in terms of appearance and spatial context. We then jointly select the best proposals across the video by solving a novel submodular problem that combines region voting and global region matching. Finally, the localization results are leveraged as strong supervision to guide pixel-level segmentation. Extensive experiments are conducted on two challenging public databases: Youtube-Objects and DAVIS. The results suggest that the proposed approach improves over previous weakly supervised/unsupervised approaches significantly, showing a performance even comparable with the several approaches supervised by the costly manual segmentations. [ABSTRACT FROM AUTHOR]

Conventional predictive video coding-based approaches are reaching the limit of their potential coding efficiency improvements, because of severely increasing computation complexity. As an alternative approach, perceptual video coding (PVC) has attempted to achieve high coding efficiency by eliminating perceptual redundancy, using just-noticeable-distortion (JND) directed PVC. The previous JNDs were modeled by adding white Gaussian noise or specific signal patterns into the original images, which were not appropriate in finding JND thresholds due to distortion with energy reduction. In this paper, we present a novel discrete cosine transform-based energy-reduced JND model, called ERJND, that is more suitable for JND-based PVC schemes. Then, the proposed ERJND model is extended to two learning-based just-noticeable-quantization-distortion (JNQD) models as preprocessing that can be applied for perceptual video coding. The two JNQD models can automatically adjust JND levels based on given quantization step sizes. One of the two JNQD models, called LR-JNQD, is based on linear regression and determines the model parameter for JNQD based on extracted handcraft features. The other JNQD model is based on a convolution neural network (CNN), called CNN-JNQD. To our best knowledge, our paper is the first approach to automatically adjust JND levels according to quantization step sizes for preprocessing the input to video encoders. In experiments, both the LR-JNQD and CNN-JNQD models were applied to high efficiency video coding (HEVC) and yielded maximum (average) bitrate reductions of 38.51% (10.38%) and 67.88% (24.91%), respectively, with little subjective video quality degradation, compared with the input without preprocessing applied. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing while considering endmember variability is usually performed by the normal compositional model, where the endmembers for each pixel are assumed to be sampled from unimodal Gaussian distributions. However, in real applications, the distribution of a material is often not Gaussian. In this paper, we use Gaussian mixture models (GMM) to represent endmember variability. We show, given the GMM starting premise, that the distribution of the mixed pixel (under the linear mixing model) is also a GMM (and this is shown from two perspectives). The first perspective originates from random variable transformations and gives a conditional density function of the pixels given the abundances and GMM parameters. With proper smoothness and sparsity prior constraints on the abundances, the conditional density function leads to a standard maximum a posteriori (MAP ) problem which can be solved using generalized expectation maximization. The second perspective originates from marginalizing over the endmembers in the GMM, which provides us with a foundation to solve for the endmembers at each pixel. Hence, compared to the other distribution based methods, our model can not only estimate the abundances and distribution parameters, but also the distinct endmember set for each pixel. We tested the proposed GMM on several synthetic and real datasets, and showed its potential by comparing it to current popular methods. [ABSTRACT FROM AUTHOR]

In this paper, we focus on improving the proposal classification stage in the object detection task and present implicit negative sub-categorization and sink diversion to lift the performance by strengthening loss function in this stage. First, based on the observation that the “background” class is generally very diverse and thus challenging to be handled as a single indiscriminative class in existing state-of-the-art methods, we propose to divide the background category into multiple implicit sub-categories to explicitly differentiate diverse patterns within it. Second, since the ground truth class inevitably has low-value probability scores for certain images, we propose to add a “sink” class and divert the probabilities of wrong classes to this class when necessary, such that the ground truth label will still have a higher probability than other wrong classes even though it has low probability output. Additionally, we propose to use dilated convolution, which is widely used in the semantic segmentation task, for efficient and valuable context information extraction. Extensive experiments on PASCAL VOC 2007 and 2012 data sets show that our proposed methods based on faster R-CNN implementation can achieve state-of-the-art mAPs, i.e., 84.1%, 82.6%, respectively, and obtain 2.5% improvement on ILSVRC DET compared with that of ResNet. [ABSTRACT FROM PUBLISHER]

Objects that do not lie at the focal distance of a digital camera generate defocused regions in the captured image. This paper presents a new edge-based method for spatially varying defocus blur estimation using a single image based on reblurred gradient magnitudes. The proposed approach initially computes a scale-consistent edge map of the input image and selects a local reblurring scale aiming to cope with noise, edge mis-localization, and interfering edges. An initial blur estimate is computed at the detected scale-consistent edge points and a novel connected edge filter is proposed to smooth the sparse blur map based on pixel connectivity within detected edge contours. Finally, a fast guided filter is used to propagate the sparse blur map through the whole image. Experimental results show that the proposed approach presents a very good compromise between estimation error and running time when compared with the state-of-the-art methods. We also explore our blur estimation method in the context of image deblurring, and show that metrics typically used to evaluate blur estimation may not correlate as expected with the visual quality of the deblurred image. [ABSTRACT FROM PUBLISHER]

In this paper, we present a simple yet effective image deblurring method to produce ringing-free deblurred images. Our work is inspired by the observation that large-scale deblurring ringing artifacts are measurable through a multi-resolution pyramid of low-pass filtering of the blurred-deblurred image pair. We propose to model such a quantification as a convex cost function and minimize it directly in the deblurring process in order to reduce ringing regardless of its cause. An efficient primal-dual algorithm is proposed as a solution to this optimization problem. Since the regularization is more biased toward ringing patterns, the details of the reconstructed image are prevented from over-smoothing. An inevitable source of ringing is sensor saturation which can be detected costlessly contrary to most other sources of ringing. However, dealing with the saturation effect in deblurring introduces a non-linear operator in optimization problem. In this paper, we also introduce a linear approximation as a solution to handling saturation in the proposed deblurring method. As a result of these steps, we significantly enhance the quality of the deblurred images. Experimental results and quantitative evaluations demonstrate that the proposed method performs favorably against state-of-the-art image deblurring methods. [ABSTRACT FROM AUTHOR]

To address the problem of face recognition with image sets, we aim to capture the underlying data distribution in each set and thus facilitate more robust classification. To this end, we represent image set as the Gaussian mixture model (GMM) comprising a number of Gaussian components with prior probabilities and seek to discriminate Gaussian components from different classes. Since in the light of information geometry, the Gaussians lie on a specific Riemannian manifold, this paper presents a method named discriminant analysis on Riemannian manifold of Gaussian distributions (DARG). We investigate several distance metrics between Gaussians and accordingly two discriminative learning frameworks are presented to meet the geometric and statistical characteristics of the specific manifold. The first framework derives a series of provably positive definite probabilistic kernels to embed the manifold to a high-dimensional Hilbert space, where conventional discriminant analysis methods developed in Euclidean space can be applied, and a weighted Kernel discriminant analysis is devised which learns discriminative representation of the Gaussian components in GMMs with their prior probabilities as sample weights. Alternatively, the other framework extends the classical graph embedding method to the manifold by utilizing the distance metrics between Gaussians to construct the adjacency graph, and hence the original manifold is embedded to a lower-dimensional and discriminative target manifold with the geometric structure preserved and the interclass separability maximized. The proposed method is evaluated by face identification and verification tasks on four most challenging and largest databases, YouTube Celebrities, COX, YouTube Face DB, and Point-and-Shoot Challenge, to demonstrate its superiority over the state-of-the-art. [ABSTRACT FROM PUBLISHER]

Studies on human motion have attracted a lot of attentions. Human motion capture data, which much more precisely records human motion than videos do, has been widely used in many areas. Motion segmentation is an indispensable step for many related applications, but current segmentation methods for motion capture data do not effectively model some important characteristics of motion capture data, such as Riemannian manifold structure and containing non-Gaussian noise. In this paper, we convert the segmentation of motion capture data into a temporal subspace clustering problem. Under the framework of sparse subspace clustering, we propose to use the geodesic exponential kernel to model the Riemannian manifold structure, use correntropy to measure the reconstruction error, use the triangle constraint to guarantee temporal continuity in each cluster and use multi-view reconstruction to extract the relations between different joints. Therefore, exploiting some special characteristics of motion capture data, we propose a new segmentation method, which is robust to non-Gaussian noise, since correntropy is a localized similarity measure. We also develop an efficient optimization algorithm based on block coordinate descent method to solve the proposed model. Our optimization algorithm has a linear complexity while sparse subspace clustering is originally a quadratic problem. Extensive experiment results both on simulated noisy data set and real noisy data set demonstrate the advantage of the proposed method. [ABSTRACT FROM PUBLISHER]

Stitching videos captured by hand-held mobile cameras can essentially enhance entertainment experience of ordinary users. However, such videos usually contain heavy shakiness and large parallax, which are challenging to stitch. In this paper, we propose a novel approach of video stitching and stabilization for videos captured by mobile devices. The main component of our method is a unified video stitching and stabilization optimization that computes stitching and stabilization simultaneously rather than does each one individually. In this way, we can obtain the best stitching and stabilization results relative to each other without any bias to one of them. To make the optimization robust, we propose a method to identify background of input videos, and also common background of them. This allows us to apply our optimization on background regions only, which is the key to handle large parallax problem. Since stitching relies on feature matches between input videos, and there inevitably exist false matches, we thus propose a method to distinguish between right and false matches, and encapsulate the false match elimination scheme and our optimization into a loop, to prevent the optimization from being affected by bad feature matches. We test the proposed approach on videos that are causally captured by smartphones when walking along busy streets, and use stitching and stability scores to evaluate the produced panoramic videos quantitatively. Experiments on a diverse of examples show that our results are much better than (challenging cases) or at least on par with (simple cases) the results of previous approaches. [ABSTRACT FROM PUBLISHER]

Driven by recent vision and graphics applications such as image segmentation and object recognition, computing pixel-accurate saliency values to uniformly highlight foreground objects becomes increasingly important. In this paper, we propose a unified framework called pixelwise image saliency aggregating (PISA) various bottom-up cues and priors. It generates spatially coherent yet detail-preserving, pixel-accurate, and fine-grained saliency, and overcomes the limitations of previous methods, which use homogeneous superpixel based and color only treatment. PISA aggregates multiple saliency cues in a global context, such as complementary color and structure contrast measures, with their spatial priors in the image domain. The saliency confidence is further jointly modeled with a neighborhood consistence constraint into an energy minimization formulation, in which each pixel will be evaluated with multiple hypothetical saliency levels. Instead of using global discrete optimization methods, we employ the cost-volume filtering technique to solve our formulation, assigning the saliency levels smoothly while preserving the edge-aware structure details. In addition, a faster version of PISA is developed using a gradient-driven image subsampling strategy to greatly improve the runtime efficiency while keeping comparable detection accuracy. Extensive experiments on a number of public data sets suggest that PISA convincingly outperforms other state-of-the-art approaches. In addition, with this work, we also create a new data set containing 800 commodity images for evaluating saliency detection. [ABSTRACT FROM PUBLISHER]

In this paper, we present and investigate an approach to fast multilabel color image segmentation using convex optimization techniques. The presented model is in some ways related to the well-known Mumford–Shah model, but deviates in certain important aspects. The optimization problem has been designed with two goals in mind. The objective function should represent fundamental concepts of image segmentation, such as incorporation of weighted curve length and variation of intensity in the segmented regions, while allowing transformation into a convex concave saddle point problem that is computationally inexpensive to solve. This paper introduces such a model, the nontrivial transformation of this model into a convex–concave saddle point problem, and the numerical treatment of the problem. We evaluate our approach by applying our algorithm to various images and show that our results are competitive in terms of quality at unprecedentedly low computation times. Our algorithm allows high-quality segmentation of megapixel images in a few seconds and achieves interactive performance for low resolution images (Fig. 1). [ABSTRACT FROM AUTHOR]

Scene appearance from the point of view of a light source is called a reciprocal or dual view. Since there exists a large diversity in illumination, these virtual views may be nonperspective and multiviewpoint in nature. In this paper, we demonstrate the use of occluding masks to recover these dual views, which we term shadow cameras. We first show how to render a single reciprocal scene view by swapping the camera and light source positions. We then extend this technique for multiple views by both building a virtual shadow camera array and by exploiting area sources. We also capture nonperspective views such as orthographic, cross-slit and a pushbroom variant, while introducing novel applications such as converting between camera projections and removing refractive and catadioptric distortions. Finally, since a shadow camera is artificial, we can manipulate any of its intrinsic parameters, such as camera skew, to create perspective distortions. We demonstrate a variety of indoor and outdoor results and show a rendering application for capturing the light-field of a light-source. [ABSTRACT FROM AUTHOR]

This paper presents a cost-sensitive ordinal hyperplanes ranking algorithm for human age estimation based on face images. The proposed approach exploits relative-order information among the age labels for rank prediction. In our approach, the age rank is obtained by aggregating a series of binary classification results, where cost sensitivities among the labels are introduced to improve the aggregating performance. In addition, we give a theoretical analysis on designing the cost of individual binary classifier so that the misranking cost can be bounded by the total misclassification costs. An efficient descriptor, scattering transform, which scatters the Gabor coefficients and pooled with Gaussian smoothing in multiple layers, is evaluated for facial feature extraction. We show that this descriptor is a generalization of conventional bioinspired features and is more effective for face-based age inference. Experimental results demonstrate that our method outperforms the state-of-the-art age estimation approaches. [ABSTRACT FROM PUBLISHER]

This paper presents a fast and flexible curve, and surface reconstruction technique based on implicit B-spline. This representation does not require any parameterization and it is locally supported. This fact has been exploited in this paper to propose a reconstruction technique through solving a sparse system of equations. This method is further accelerated to reduce the dimension to the active control lattice. Moreover, the surface smoothness and user interaction are allowed for controlling the surface. Finally, a novel weighting technique has been introduced in order to blend small patches and smooth them in the overlapping regions. The whole framework is very fast and efficient and can handle large cloud of points with very low computational cost. The experimental results show the flexibility and accuracy of the proposed algorithm to describe objects with complex topologies. Comparisons with other fitting methods highlight the superiority of the proposed approach in the presence of noise and missing data. [ABSTRACT FROM AUTHOR]

Domain adaptation has been a fundamental technology for transferring knowledge from a source domain to a target domain. The key issue of domain adaptation is how to reduce the distribution discrepancy between two domains in a proper way such that they can be treated indifferently for learning. In this paper, we propose a novel domain adaptation approach, which can thoroughly explore the data distribution structure of target domain. Specifically, we regard the samples within the same cluster in target domain as a whole rather than individuals and assigns pseudo-labels to the target cluster by class centroid matching. Besides, to exploit the manifold structure information of target data more thoroughly, we further introduce a local manifold self-learning strategy into our proposal to adaptively capture the inherent local connectivity of target samples. An efficient iterative optimization algorithm is designed to solve the objective function of our proposal with theoretical convergence guarantee. In addition to unsupervised domain adaptation, we further extend our method to the semi-supervised scenario including both homogeneous and heterogeneous settings in a direct but elegant way. Extensive experiments on seven benchmark datasets validate the significant superiority of our proposal in both unsupervised and semi-supervised manners. [ABSTRACT FROM AUTHOR]

Local feature descriptor learning aims to represent distinctive images or patches with the same local features, where their representation is invariant under different types of deformation. Recent studies have demonstrated that descriptor learning based on Convolutional Neural Network (CNN) is able to improve the matching performance significantly. However, they tend to ignore the importance of sample selection during the training process, leading to unstable quality of descriptors and learning efficiency. In this paper, a dual hard batch construction method is proposed to sample the hard matching and non-matching examples for training, improving the performance of the descriptor learning on different tasks. To construct the dual hard training batches, the matching examples with the minimum similarity are selected as the hard positive pairs. For each positive pair, the most similar non-matching example is then sampled from the generated hard positive pairs in the same batch as the corresponding negative. By sampling the hard positive pairs and the corresponding hard negatives, the hard batches are produced to force the CNN model to learn the descriptors with more efforts. In addition, based on the above dual hard batch construction, an $\ell _{2}^{2}$ triplet loss function is built for optimizing the training model. Specifically, we analyze the superiority of the $\ell _{2}^{2}$ loss function when dealing with hard examples, and also demonstrate it in the experiments. With the benefits of the proposed sampling strategy and the $\ell _{2}^{2}$ triplet loss function, our method achieves better performance compared to state-of-the-art on the reference benchmarks for different matching tasks. [ABSTRACT FROM AUTHOR]

In a recent study, it was shown that, with adversarial training of an attentive generative network, it is possible to convert a raindrop degraded image into a relatively clean one. However, in real world, raindrop appearance is not only formed by individual raindrops, but also by the distant raindrops accumulation and the atmospheric veiling, namely haze. Current methods are limited in extracting accurate features from a raindrop degraded image with background scene, the blurred raindrop regions, and the haze. In this paper, we propose a new model for an image corrupted by the raindrops and the haze, and introduce an integrated multi-task algorithm to address the joint raindrop and haze removal (JRHR) problem by combining an improved estimate of the atmospheric light, a modified transmission map, a generative adversarial network (GAN) and an optimized visual attention network. The proposed algorithm can extract more accurate features for both sky and non-sky regions. Experimental evaluation has been conducted to show that the proposed algorithm significantly outperforms state-of-the-art algorithms on both synthetic and real-world images in terms of both qualitative and quantitative measures. [ABSTRACT FROM AUTHOR]

Recently, infrared small target detection problem has attracted substantial attention. Many works based on local low-rank model have been proven to be very successful for enhancing the discriminability during detection. However, these methods construct patches by traversing local images and ignore the correlations among different patches. Although the calculation is simplified, some texture information of the target is ignored, and targets of arbitrary forms cannot be accurately identified. In this paper, a novel target-aware method based on a non-local low-rank model and saliency filter regularization is proposed, with which the newly proposed detection framework can be tailored as a non-convex optimization problem, therein enabling joint target saliency learning in a lower dimensional discriminative manifold. More specifically, non-local patch construction is applied for the proposed target-aware low-rank model. By combining similar patches, we reconstruct them together to achieve a better generalization of non-local spatial sparsity constraints. Furthermore, to encourage target saliency learning, our proposed saliency filtering regularization term based on entropy is restricted to lie between the background and foreground. The regularization of the saliency filtering locally preserves the contexts from the target and surrounding areas and avoids the deviated approximation of the low-rank matrix. Finally, a unified optimization framework is proposed and solved with the alternative direction multiplier method (ADMM). Experimental evaluations of real infrared images demonstrate that the proposed method is more robust under different complex scenes compared with some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper revisits the problem of rate distortion optimization (RDO) with focus on inter-picture dependence. A joint RDO framework which incorporates the Lagrange multiplier as one of parameters to be optimized is proposed. Simplification strategies are demonstrated for practical applications. To make the problem tractable, we consider an approach where prediction residuals of pictures in a video sequence are assumed to be emitted from a finite set of sources. Consequently the RDO problem is formulated as finding optimal coding parameters for a finite number of sources, regardless of the length of the video sequence. Specifically, in cases where a hierarchical prediction structure is used, prediction residuals of pictures at the same prediction layer are assumed to be emitted from a common source. Following this approach, we propose an iterative algorithm to alternatively optimize the selections of quantization parameters (QPs) and the corresponding Lagrange multipliers. Based on the results of the iterative algorithm, we further propose two practical algorithms to compute QPs and the Lagrange multipliers for the RA(random access) hierarchical video coding: the first practical algorithm uses a fixed formula to compute QPs and the Lagrange multipliers, and the second practical algorithm adaptively adjusts both QPs and the Lagrange multipliers. Experimental results show that these three algorithms, integrated into the HM 16.20 reference software of HEVC, can achieve considerable RD improvements over the standard HM 16.20 encoder, in the common RA test configuration. [ABSTRACT FROM AUTHOR]

In many state-of-the-art compression systems, signal transformation is an integral part of the encoding and decoding process, where transforms provide compact representations for the signals of interest. This paper introduces a class of transforms called graph-based transforms (GBTs) for video compression, and proposes two different techniques to design GBTs. In the first technique, we formulate an optimization problem to learn graphs from data and provide solutions for optimal separable and nonseparable GBT designs, called GL-GBTs. The optimality of the proposed GL-GBTs is also theoretically analyzed based on Gaussian-Markov random field (GMRF) models for intra and inter predicted block signals. The second technique develops edge-adaptive GBTs (EA-GBTs) in order to flexibly adapt transforms to block signals with image edges (discontinuities). The advantages of EA-GBTs are both theoretically and empirically demonstrated. Our experimental results show that the proposed transforms can significantly outperform the traditional Karhunen-Loeve transform (KLT). [ABSTRACT FROM AUTHOR]

Various weather conditions, such as rain, haze, or snow, can degrade visual quality in images/videos, which may significantly degrade the performance of related applications. In this paper, a novel framework based on sequential dual attention deep network is proposed for removing rain streaks (deraining) in a single image, called by SSDRNet (Sequential dual attention-based Single image DeRaining deep Network). Since the inherent correlation among rain steaks within an image should be stronger than that between the rain streaks and the background (non-rain) pixels, a two-stage learning strategy is implemented to better capture the distribution of rain streaks within a rainy image. The two-stage deep neural network primarily involves three blocks: residual dense blocks (RDBs), sequential dual attention blocks (SDABs), and multi-scale feature aggregation modules (MAMs), which are all delicately and specifically designed for rain removal. The two-stage strategy successfully learns very fine details of the rain steaks of the image and then clearly removes them. Extensive experimental results have shown that the proposed deep framework achieves the best performance on qualitative and quantitative metrics compared with state-of-the-art methods. The corresponding code and the trained model of the proposed SSDRNet have been available online at https://github.com/fityanul/SDAN-for-Rain-Removal. [ABSTRACT FROM AUTHOR]

Image compression has always been an important topic in the last decades due to the explosive increase of images. The popular image compression formats are based on different transforms which convert images from the spatial domain into compact frequency domain to remove the spatial correlation. In this paper, we focus on the exploration of data-driven transform, Karhunen-Loéve transform (KLT), the kernels of which are derived from specific images via Principal Component Analysis (PCA), and design a high efficient KLT based image compression algorithm with variable transform sizes. To explore the optimal compression performance, the multiple transform sizes and categories are utilized and determined adaptively according to their rate-distortion (RD) costs. Moreover, comprehensive analyses on the transform coefficients are provided and a band-adaptive quantization scheme is proposed based on the coefficient RD performance. Extensive experiments are performed on several class-specific images as well as general images, and the proposed method achieves significant coding gain over the popular image compression standards including JPEG, JPEG 2000, and the state-of-the-art dictionary learning based methods. [ABSTRACT FROM AUTHOR]

Change detection has received extensive attention because of its realistic significance and broad application fields. However, none of the existing change detection algorithms can handle all scenarios and tasks so far. Different from the most of contributions from the research community in recent years, this paper does not work on designing new change detection algorithms. We, instead, solve the problem from another perspective by enhancing the raw detection results after change detection. As a result, the proposed method is applicable to various kinds of change detection methods, and regardless of how the results are detected. In this paper, we propose Fast Spatiotemporal Tree Filter (FSTF), a purely unsupervised detection method, to enhance coarse binary detection masks obtained by different kinds of change detection methods. In detail, the proposed FSTF has adopted a volumetric structure to effectively synthesize spatiotemporal information of the same target from the current time and history frames to enhance detection. The computational complexity analyzed in the view of graph theory also show that the fast realization of FSTF is a linear time algorithm, which is capable of handling efficient on-line detection tasks. Finally, comprehensive experiments based on qualitative and quantitative analysis verify that FSTF-based change detection enhancement is superior to several other state-of-the-art methods including fully connected Conditional Random Field (CRF), joint bilateral filter, and guided filter. It is illustrated that FSTF is versatile enough to also improve saliency detection as well as semantic image segmentation. [ABSTRACT FROM AUTHOR]

This paper proposes a novel bi-directional motion compensation framework that extracts existing motion information associated with the reference frames and interpolates an additional reference frame candidate that is co-located with the current frame. The approach generates a dense motion field by performing optical flow estimation, so as to capture complex motion between the reference frames without recourse to additional side information. The estimated optical flow is then complemented by transmission of offset motion vectors to correct for possible deviation from the linearity assumption in the interpolation. Various optimization schemes specifically tailored to the video coding framework are presented to further improve the performance. To accommodate applications where decoder complexity is a cardinal concern, a block-constrained speed-up algorithm is also proposed. Experimental results show that the main approach and optimization methods yield significant coding gains across a diverse set of video sequences. Further experiments focus on the trade-off between performance and complexity, and demonstrate that the proposed speed-up algorithm offers complexity reduction by a large factor while maintaining most of the performance gains. [ABSTRACT FROM AUTHOR]

Crowd counting is a challenging problem due to the diverse crowd distribution and background interference. In this paper, we propose a new approach for head size estimation to reduce the impact of different crowd scale and background noise. Different from just using local information of distance between human heads, the global information of the people distribution in the whole image is also under consideration. We obey the order of far- to near-region (small to large) to spread head size, and ensure that the propagation is uninterrupted by inserting dummy head points. The estimated head size is further exploited, such as dividing the crowd into parts of different densities and generating a high-fidelity head mask. On the other hand, we design three different head mask usage mechanisms and the corresponding head masks to analyze where and which mask could lead to better background filtering. Based on the learned masks, two competitive models are proposed which can perform robust crowd estimation against background noise and diverse crowd scale. We evaluate the proposed method on three public crowd counting datasets of ShanghaiTech, UCFQNRF and UCFCC_50. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art crowd counting approaches. [ABSTRACT FROM AUTHOR]

Estimating optical flow from successive video frames is one of the fundamental problems in computer vision and image processing. In the era of deep learning, many methods have been proposed to use convolutional neural networks (CNNs) for optical flow estimation in an unsupervised manner. However, the performance of unsupervised optical flow approaches is still unsatisfactory and often lagging far behind their supervised counterparts, primarily due to over-smoothing across motion boundaries and occlusion. To address these issues, in this paper, we propose a novel method with a new post-processing term and an effective loss function to estimate optical flow in an unsupervised, end-to-end learning manner. Specifically, we first exploit a CNN-based non-local term to refine the estimated optical flow by removing noise and decreasing blur around motion boundaries. This is implemented via automatically learning weights of dependencies over a large spatial neighborhood. Because of its learning ability, the method is effective for various complicated image sequences. Secondly, to reduce the influence of occlusion, a symmetrical energy formulation is introduced to detect the occlusion map from refined bi-directional optical flows. Then the occlusion map is integrated to the loss function. Extensive experiments are conducted on challenging datasets, i.e. FlyingChairs, MPI-Sintel and KITTI to evaluate the performance of the proposed method. The state-of-the-art results demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel color constancy approach, called Bag of Color Features (BoCF), building upon Bag-of-Features pooling. The proposed method substantially reduces the number of parameters needed for illumination estimation. At the same time, the proposed method is consistent with the color constancy assumption stating that global spatial information is not relevant for illumination estimation and local information (edges, etc.) is sufficient. Furthermore, BoCF is consistent with color constancy statistical approaches and can be interpreted as a learning-based extension of many statistical approaches. To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention. BoCF approach and its variants achieve competitive, compared to the state of the art, results while requiring much fewer parameters on three benchmark datasets: ColorChecker RECommended, INTEL-TUT version 2, and NUS8. [ABSTRACT FROM AUTHOR]

In this paper, we propose a just noticeable distortion (JND)-based perceptual rate control method for high efficiency video coding (HEVC). First, the JND factor of a coding unit has been mathematically shown to be an approximation of the average pixel-level JND weight, which means that it can also be used as a weight for bitrate allocation. Second, rate-distortion (R-D) modelling is conducted based on the JND factor. Finally, the proposed R-D model is integrated into an existing rate control framework to improve the coding efficiency, and the proposed algorithm is implemented in the newest video coding standard. As the experimental results reveal, compared with HEVC reference software, our algorithm achieves significantly improved coding performance, subjective coding quality and bitrate accuracy. [ABSTRACT FROM AUTHOR]

Visually unpleasant compression artifacts frequently appear in block-based transform coding, especially at low bit rates. This paper presents a new artifact reduction scheme based on Bayesian sparse modeling and artifacts-free PCA basis learning. To avoid the effect of blocking artifacts, we propose to learn artifacts-free PCA basis from clean images. We concatenate the clean patches and their compressed counterparts to learn paired distribution prior via the Gaussian Mixture Model (GMM). By this way, the GMM characterizes the mapping between the clean image and its compressed version. To restore a compressed patch, the best matched GMM component is assigned using the patch in the compressed image subspace. The artifacts-free PCA basis is obtained according to the mapping learned by the paired GMM. In practice, the statistical distributions of different sparse coefficients in different patches may dramatically vary with image contents. Instead of using a global zero-mean distribution for all coefficients, we propose to adaptively model the prior of each band in a Bayesian framework. The expectation and variance of each band are adaptively learned from the similar patches within the image. Thus, different transform bands are regularized unequally according to the learned priors. Experimental results show that the proposed scheme outperforms most of the compared schemes in terms of both objective quality and perceptual quality. [ABSTRACT FROM AUTHOR]

The main aim of this paper is to develop a framelet representation of the tensor nuclear norm for third-order tensor recovery. In the literature, the tensor nuclear norm can be computed by using tensor singular value decomposition based on the discrete Fourier transform matrix, and tensor completion can be performed by the minimization of the tensor nuclear norm which is the relaxation of the sum of matrix ranks from all Fourier transformed matrix frontal slices. These Fourier transformed matrix frontal slices are obtained by applying the discrete Fourier transform on the tubes of the original tensor. In this paper, we propose to employ the framelet representation of each tube so that a framelet transformed tensor can be constructed. Because of framelet basis redundancy, the representation of each tube is sparsely represented. When the matrix slices of the original tensor are highly correlated, we expect the corresponding sum of matrix ranks from all framelet transformed matrix frontal slices would be small, and the resulting tensor completion can be performed much better. The proposed minimization model is convex and global minimizers can be obtained. Numerical results on several types of multi-dimensional data (videos, multispectral images, and magnetic resonance imaging data) have tested and shown that the proposed method outperformed the other testing methods. [ABSTRACT FROM AUTHOR]

Existing successful person re-identification (Re-ID) models often employ the part-level representation to extract the fine-grained information, but commonly use the loss that is particularly designed for global features, ignoring the relationship between semantic parts. In this paper, we present a novel triplet loss that emphasizes the salient parts and also takes the consideration of alignment. This loss is based on the crossing-bing matching metric that also known as Wasserstein Distance. It measures how much effort it would take to move the embeddings of local features to align two distributions, such that it is able to find an optimal transport matrix to re-weight the distance of different local parts. The distributions in support of local parts is produced via a new attention mechanism, which is calculated by the inner product between high-level global feature and local features, representing the importance of different semantic parts w.r.t. identification. We show that the obtained optimal transport matrix can not only distinguish the relevant and misleading parts, and hence assign different weights to them, but also rectify the original distance according to the learned distributions, resulting in an elegant solution for the mis-alignment issue. Besides, the proposed method is easily implemented in most Re-ID learning system with end-to-end training style, and can obviously improve their performance. Extensive experiments and comparisons with recent Re-ID methods manifest the competitive performance of our method. [ABSTRACT FROM AUTHOR]

Despite the promise of recent deep neural networks to provide more accurate and efficient iris recognition compared to traditional techniques, there are vital properties of the classic IrisCode which are almost unable to be achieved with current deep iris networks: the compactness of model and the small number of computing operations (FLOPs). This paper casts the iris network design process as a constrained optimization problem which takes model size and computation into account as learning criteria. On one hand, this allows us to fully automate the network design process to search for the optimal iris network architecture with the highest recognition accuracy confined to the computation and model compactness constraints. On the other hand, it allows us to investigate the optimality of the classic IrisCode and recent deep iris networks. It also enables us to learn an optimal iris network and demonstrate state-of-the-art performance with less computation and memory requirements. [ABSTRACT FROM AUTHOR]

Integer Linear Programming (ILP) formulations of multi-label Markov random fields (MRFs) models with global connectivity priors were investigated previously in computer vision. In these works, only Linear Programming (LP) relaxations or simplified versions of the problem were solved. This paper investigates the ILP of MRF with exact connectivity priors via a branch-and-cut method, which provably finds globally optimal solutions. It enforces connectivity priors iteratively by a cutting plane method, and provides feasible solutions with a guarantee on sub-optimality even if we terminate it earlier. The proposed ILP can be applied as a post-processing method on top of any existing multi-label segmentation approach. As it provides globally optimal solution, it can be used off-line to serve as quality check for any fast on-line algorithm. Furthermore, the scribble based model presented in this paper could be potentially used to generate ground-truth proposals for any deep learning based segmentation. We demonstrate the power and usefulness of our model by extensive experiments on the BSDS500 and PASCAL VOC dataset. The experiments show that our proposed model achieves great performance, yielding provably global optimum in most instances and that provably good optimization solutions also provide good segmentation accuracy, even with the limited computing time of few seconds. [ABSTRACT FROM AUTHOR]

In capsule networks (CapsNets), the capsule is made up of collections of neurons. Their adjacent capsule layers are connected using routing-by-agreement mechanisms in an unsupervised way. The routing-by-agreement mechanisms have two main drawbacks: a) too many parameters and high computation complexity; b) the cluster distribution assumptions of these routing mechanisms may not hold in some complex real-world data. In this paper, we propose a novel Group Feedback Capsule Network (GF-CapsNet) which adopts a supervised routing strategy called group-routing. Compared with the previous routing strategies which globally transform each capsule, Group-routing equally splits capsules into groups where capsules locally share the same transformation weights, reducing routing parameters. To address the second drawback, we devise a distance network to directly predict capsules in a supervised way without making distribution assumptions. Our proposed group-routing captures local information of low-level capsules by group-wise transformation and supervisedly predicts high-level ones in a feedback way to address two drawbacks respectively. We conduct experiments on CIFAR-10/100 and SVHN datasets and the results show that our method can perform better against state-of-the-arts. [ABSTRACT FROM AUTHOR]