Search

Most researchers focus on designing accurate crowd counting models with heavy parameters and computations but ignore the resource burden during the model deployment. A real-world scenario demands an efficient counting model with low-latency and high-performance. Knowledge distillation provides an elegant way to transfer knowledge from a complicated teacher model to a compact student model while maintaining accuracy. However, the student model receives the wrong guidance with the supervision of the teacher model due to the inaccurate information understood by the teacher in some cases. In this paper, we propose a dual-knowledge distillation (DKD) framework, which aims to reduce the side effects of the teacher model and transfer hierarchical knowledge to obtain a more efficient counting model. First, the student model is initialized with global information transferred by the teacher model via adaptive perspectives. Then, the self-knowledge distillation forces the student model to learn the knowledge by itself, based on intermediate feature maps and target map. Specifically, the optimal transport distance is utilized to measure the difference of feature maps between the teacher and the student to perform the distribution alignment of the counting area. Extensive experiments are conducted on four challenging datasets, demonstrating the superiority of DKD. When there are only approximately 6% of the parameters and computations from the original models, the student model achieves a faster and more accurate counting performance as the teacher model even surpasses it. [ABSTRACT FROM AUTHOR]

Scene flow represents the 3D motion of every point in the dynamic environments. Like the optical flow that represents the motion of pixels in 2D images, 3D motion representation of scene flow benefits many applications, such as autonomous driving and service robot. This paper studies the problem of scene flow estimation from two consecutive 3D point clouds. In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer. The proposed network has a new more-for-less hierarchical architecture. The more-for-less means that the number of input points is greater than the number of output points for scene flow estimation, which brings more input information and balances the precision and resource consumption. In this hierarchical architecture, scene flow of different levels is generated and supervised respectively. A novel attentive embedding module is introduced to aggregate the features of adjacent points using a double attention method in a patch-to-patch manner. The proper layers for flow embedding and flow supervision are carefully considered in our network designment. Experiments show that the proposed network outperforms the state-of-the-art performance of 3D scene flow estimation on the FlyingThings3D and KITTI Scene Flow 2015 datasets. We also apply the proposed network to the realistic LiDAR odometry task, which is a key problem in autonomous driving. The experiment results demonstrate that our proposed network can outperform the ICP-based method and shows good practical application ability. The source codes will be released on https://github.com/IRMVLab/HALFlow. [ABSTRACT FROM AUTHOR]

Human-Object Interaction (HOI) detection recognizes how persons interact with objects, which is advantageous in autonomous systems such as self-driving vehicles and collaborative robots. However, current HOI detectors are often plagued by model inefficiency and unreliability when making a prediction, which consequently limits its potential for real-world scenarios. In this paper, we address these challenges by proposing ERNet, an end-to-end trainable convolutional-transformer network for HOI detection. The proposed model employs an efficient multi-scale deformable attention to effectively capture vital HOI features. We also put forward a novel detection attention module to adaptively generate semantically rich instance and interaction tokens. These tokens undergo pre-emptive detections to produce initial region and vector proposals that also serve as queries which enhances the feature refinement process in the transformer decoders. Several impactful enhancements are also applied to improve the HOI representation learning. Additionally, we utilize a predictive uncertainty estimation framework in the instance and interaction classification heads to quantify the uncertainty behind each prediction. By doing so, we can accurately and reliably predict HOIs even under challenging scenarios. Experiment results on the HICO-Det, V-COCO, and HOI-A datasets demonstrate that the proposed model achieves state-of-the-art performance in detection accuracy and training efficiency. Codes are publicly available at https://github.com/Monash-CyPhi-AI-Research-Lab/ernet. [ABSTRACT FROM AUTHOR]

Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain. [ABSTRACT FROM AUTHOR]

Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical flow estimation methods are based on two consecutive image frames and can only estimate discrete flow at a fixed time interval. Previous work has shown that continuous flow estimation can be achieved by changing the quantities or time intervals of events. However, they are difficult to estimate reliable dense flow, especially in the regions without any triggered events. In this paper, we propose a novel deep learning-based dense and continuous optical flow estimation framework from a single image with event streams, which facilitates the accurate perception of high-speed motion. Specifically, we first propose an event-image fusion and correlation module to effectively exploit the internal motion from two different modalities of data. Then we propose an iterative update network structure with bidirectional training for optical flow prediction. Therefore, our model can estimate reliable dense flow as two-frame-based methods, as well as estimate temporal continuous flow as event-based methods. Extensive experimental results on both synthetic and real captured datasets demonstrate that our model outperforms existing event-based state-of-the-art methods and our designed baselines for accurate dense and continuous optical flow estimation. [ABSTRACT FROM AUTHOR]

This paper presents a scalable approximate Bayesian method for image restoration using Total Variation (TV) priors, with the ability to offer uncertainty quantification. In contrast to most optimization methods based on maximum a posteriori estimation, we use the Expectation Propagation (EP) framework to approximate minimum mean squared error (MMSE) estimates and marginal (pixel-wise) variances, without resorting to Monte Carlo sampling. For the classical anisotropic TV-based prior, we also propose an iterative scheme to automatically adjust the regularization parameter via Expectation Maximization (EM). Using Gaussian approximating densities with diagonal covariance matrices, the resulting method allows highly parallelizable steps and can scale to large images for denoising, deconvolution, and compressive sensing (CS) problems. The simulation results illustrate that such EP methods can provide a posteriori estimates on par with those obtained via sampling methods but at a fraction of the computational cost. Moreover, EP does not exhibit strong underestimation of posteriori variances, in contrast to variational Bayes alternatives. [ABSTRACT FROM AUTHOR]

Feature matching is a fundamental problem in many computer vision tasks. This paper proposes a novel effective framework for mismatch removal, named LOcality-guided Global-preserving Optimization (LOGO). To identify inliers from a putative matching set generated by feature descriptor similarity, we introduce a fixed-point progressive approach to optimize a graph-based objective, which represents a two-class assignment problem regarding an affinity matrix containing global structures. We introduce a strategy that a small initial set with a high inlier ratio exploits the topology of the affinity matrix to elicit other inliers based on their reliable geometry, which enhances the robustness to outliers. Geometrically, we provide a locality-guided matching strategy, i.e., using local topology consensus as a criterion to determine the initial set, thus expanding to yield the final feature matching set. In addition, we apply local affine transformations based on reference points to determine the local consensus and similarity scores of nodes and edges, ensuring the validity and generality for various scenarios including complex nonrigid transformations. Extensive experiments demonstrate the effectiveness and robustness of the proposed LOGO, which is competitive with the current state-of-the-art methods. It also exhibits favorable potential for high-level vision tasks, such as essential and fundamental matrix estimation, image registration and loop closure detection. [ABSTRACT FROM AUTHOR]

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

Different people age in different ways. Learning a personalized age estimator for each person is a promising direction for age estimation given that it better models the personalization of aging processes. However, most existing personalized methods suffer from the lack of large-scale datasets due to the high-level requirements: identity labels and enough samples for each person to form a long-term aging pattern. In this paper, we aim to learn personalized age estimators without the above requirements and propose a meta-learning method named MetaAge for age estimation. Unlike most existing personalized methods that learn the parameters of a personalized estimator for each person in the training set, our method learns the mapping from identity information to age estimator parameters. Specifically, we introduce a personalized estimator meta-learner, which takes identity features as the input and outputs the parameters of customized estimators. In this way, our method learns the meta knowledge without the above requirements and seamlessly transfers the learned meta knowledge to the test set, which enables us to leverage the existing large-scale age datasets without any additional annotations. Extensive experimental results on three benchmark datasets including MORPH II, ChaLearn LAP 2015 and ChaLearn LAP 2016 databases demonstrate that our MetaAge significantly boosts the performance of existing personalized methods and outperforms the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Unsupervised domain adaptation (UDA) enables a learning machine to adapt from a labeled source domain to an unlabeled target domain under the distribution shift. Thanks to the strong representation ability of deep neural networks, recent remarkable achievements in UDA resort to learning domain-invariant features. Intuitively, the goal is that a good feature representation and the hypothesis learned from the source domain can generalize well to the target domain. However, the learning processes of domain-invariant features and source hypotheses inevitably involve domain-specific information that would degrade the generalizability of UDA models on the target domain. The lottery ticket hypothesis proves that only partial parameters are essential for generalization. Motivated by it, we find in this paper that only partial parameters are essential for learning domain-invariant information. Such parameters are termed transferable parameters that can generalize well in UDA. In contrast, the rest parameters tend to fit domain-specific details and often cause the failure of generalization, which are termed untransferable parameters. Driven by this insight, we propose Transferable Parameter Learning (TransPar) to reduce the side effect of domain-specific information in the learning process and thus enhance the memorization of domain-invariant information. Specifically, according to the distribution discrepancy degree, we divide all parameters into transferable and untransferable ones in each training iteration. We then perform separate update rules for the two types of parameters. Extensive experiments on image classification and regression tasks (keypoint detection) show that TransPar outperforms prior arts by non-trivial margins. Moreover, experiments demonstrate that TransPar can be integrated into the most popular deep UDA networks and be easily extended to handle any data distribution shift scenarios. [ABSTRACT FROM AUTHOR]

Previous deep learning-based video stabilizers require a large scale of paired unstable and stable videos for training, which are difficult to collect. Traditional trajectory-based stabilizers, on the other hand, divide the task into several sub-tasks and tackle them subsequently, which are fragile in textureless and occluded regions regarding the usage of hand-crafted features. In this paper, we attempt to tackle the video stabilization problem in a deep unsupervised learning manner, which borrows the divide-and-conquer idea from traditional stabilizers while leveraging the representation power of DNNs to handle the challenges in real-world scenarios. Technically, DUT is composed of a trajectory estimation stage and a trajectory smoothing stage. In the trajectory estimation stage, we first estimate the motion of keypoints, initialize and refine the motion of grids via a novel multi-homography estimation strategy and a motion refinement network, respectively, and get the grid-based trajectories via temporal association. In the trajectory smoothing stage, we devise a novel network to predict dynamic smoothing kernels for trajectory smoothing, which can well adapt to trajectories with different dynamic patterns. We exploit the spatial and temporal coherence of keypoints and grid vertices to formulate the training objectives, resulting in an unsupervised training scheme. Experiment results on public benchmarks show that DUT outperforms state-of-the-art methods both qualitatively and quantitatively. The source code is available at https://github.com/Annbless/DUTCode. [ABSTRACT FROM AUTHOR]

Multiview video coding (MVC) aims to compress the multiview video through the elimination of video redundancies, where the quality of the reference frame directly affects the compression efficiency. In this paper, we propose a deep virtual reference frame generation method based on a disparity-aware reference frame generation network (DAG-Net) to transform the disparity relationship between different viewpoints and generate a more reliable reference frame. The proposed DAG-Net consists of a multi-level receptive field module, a disparity-aware alignment module, and a fusion reconstruction module. First, a multi-level receptive field module is designed to enlarge the receptive field, and extract the multi-scale deep features of the temporal and inter-view reference frames. Then, a disparity-aware alignment module is proposed to learn the disparity relationship, and perform disparity shift on the inter-view reference frame to align it with the temporal reference frame. Finally, a fusion reconstruction module is utilized to fuse the complementary information and generate a more reliable virtual reference frame. Experiments demonstrate that the proposed reference frame generation method achieves superior performance for multiview video coding. [ABSTRACT FROM AUTHOR]

Low-light imaging on mobile devices is typically challenging due to insufficient incident light coming through the relatively small aperture, resulting in low image quality. Most of the previous works on low-light imaging focus either only on a single task such as illumination adjustment, color enhancement, or noise removal; or on a joint illumination adjustment and denoising task that heavily relies on short-long exposure image pairs from specific camera models. These approaches are less practical and generalizable in real-world settings where camera-specific joint enhancement and restoration is required. In this paper, we propose a low-light imaging framework that performs joint illumination adjustment, color enhancement, and denoising to tackle this problem. Considering the difficulty in model-specific data collection and the ultra-high definition of the captured images, we design two branches: a coefficient estimation branch and a joint operation branch. The coefficient estimation branch works in a low-resolution space and predicts the coefficients for enhancement via bilateral learning, whereas the joint operation branch works in a full-resolution space and progressively performs joint enhancement and denoising. In contrast to existing methods, our framework does not need to recollect massive data when adapted to another camera model, which significantly reduces the efforts required to fine-tune our approach for practical usage. Through extensive experiments, we demonstrate its great potential in real-world low-light imaging applications. [ABSTRACT FROM AUTHOR]

Inferring the scene illumination from a single image is an essential yet challenging task in computer vision and computer graphics. Existing works estimate lighting by regressing representative illumination parameters or generating illumination maps directly. However, these methods often suffer from poor accuracy and generalization. This paper presents Geometric Mover’s Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation. We parameterize illumination scenes in terms of the geometric light distribution, light intensity, ambient term, and auxiliary depth, which can be estimated by a regression network. Inspired by the earth mover’s distance, we design a novel geometric mover’s loss to guide the accurate regression of light distribution parameters. With the estimated light parameters, the generative projector synthesizes panoramic illumination maps with realistic appearance and high-frequency details. Extensive experiments show that GMLight achieves accurate illumination estimation and superior fidelity in relighting for 3D object insertion. The codes are available at https://github.com/fnzhan/Illumination-Estimation [ABSTRACT FROM AUTHOR]

Deconvolutional networks have attracted extensive attention and have been successfully applied in the field of computer vision. In this paper we propose a novel two-branch deconvolutional network (TBDN) that can improve the performance of conventional deconvolutional networks and reduce the computational complexity. A feasible iterative algorithm is designed to solve the optimization problem for the TBDN model, and a theoretical analysis of the convergence and computational complexity for the algorithm is also provided. The application of the TBDN in stereo matching is presented by constructing a disparity estimation network. Extensive experimental results on four commonly used datasets demonstrate the efficiency and effectiveness of the proposed TBDN. [ABSTRACT FROM AUTHOR]

Data associations in multi-target multi-camera tracking (MTMCT) usually estimate affinity directly from re-identification (re-ID) feature distances. However, we argue that it might not be the best choice given the difference in matching scopes between re-ID and MTMCT problems. Re-ID systems focus on global matching, which retrieves targets from all cameras and all times. In contrast, data association in tracking is a local matching problem, since its candidates only come from neighboring locations and time frames. In this paper, we design experiments to verify such misfit between global re-ID feature distances and local matching in tracking, and propose a simple yet effective approach to adapt affinity estimations to corresponding matching scopes in MTMCT. Instead of trying to deal with all appearance changes, we tailor the affinity metric to specialize in ones that might emerge during data associations. To this end, we introduce a new data sampling scheme with temporal windows originally used for data associations in tracking. Minimizing the mismatch, the adaptive affinity module brings significant improvements over global re-ID distance, and produces competitive performance on CityFlow and DukeMTMC datasets. [ABSTRACT FROM AUTHOR]

Different from the object motion blur, the defocus blur is caused by the limitation of the cameras’ depth of field. The defocus amount can be characterized by the parameter of point spread function and thus forms a defocus map. In this paper, we propose a new network architecture called Defocus Image Deblurring Auxiliary Learning Net (DID-ANet), which is specifically designed for single image defocus deblurring by using defocus map estimation as auxiliary task to improve the deblurring result. To facilitate the training of the network, we build a novel and large-scale dataset for single image defocus deblurring, which contains the defocus images, the defocus maps and the all-sharp images. To the best of our knowledge, the new dataset is the first large-scale defocus deblurring dataset for training deep networks. Moreover, the experimental results demonstrate that the proposed DID-ANet outperforms the state-of-the-art methods for both tasks of defocus image deblurring and defocus map estimation, both quantitatively and qualitatively. The dataset, code, and model is available on GitHub: https://github.com/xytmhy/DID-ANet-Defocus-Deblurring. [ABSTRACT FROM AUTHOR]

In this paper, a new statistical model is proposed for the single image super-resolution of retinal Optical Coherence Tomography (OCT) images. OCT imaging relies on interfero-metry, which explains why OCT images suffer from a high level of noise. Moreover, data subsampling is carried out during the acquisition of OCT A-scans and B-scans. So, it is necessary to utilize effective super-resolution algorithms to reconstruct high-resolution clean OCT images. In this paper, a nonlocal sparse model-based Bayesian framework is proposed for OCT restoration. For this reason, by characterizing nonlocal patches with similar structures, known as a group, the sparse coefficients of each group of OCT images are modeled by the scale mixture models. In this base, the coefficient vector is decomposed into the point-wise product of a random vector and a positive scaling variable. Estimation of the sparse coefficients depends on the proposed distribution for the random vector and scaling variable where the Laplacian random vector and Generalized Extreme-Value (GEV) scale parameter (Laplacian+GEV model) show the best goodness of fit for each group of OCT images. Finally, a new OCT super-resolution method based on this new scale mixture model is introduced, where the maximum a posterior estimation of both sparse coefficients and scaling variables are calculated efficiently by applying an alternating minimization method. Our experimental results prove that the proposed OCT super-resolution method based on the Laplacian+GEV model outperforms other competing methods in terms of both subjective and objective visual qualities. [ABSTRACT FROM AUTHOR]

As more and more satellites are launched into the space, dynamic estimation of spin satellites has become a critical component of the space situation awareness application. Some explored studies using exterior measurements from different sensors such as optical device and inverse synthetic aperture radar (ISAR) to estimate dynamic parameters of spin satellites. As a single sensor normally provides two-dimensional observation, three-dimensional estimations resulting from these algorithms are strictly related to the prior knowledge of targets characteristics. As a result, it is difficult to expand these methods to other satellites. In order to support the dynamic estimation of most spin satellites, this paper presents a novel dynamic estimation approach which employs synchronized optical-and-radar images. The optical-and-radar fusion strategy has demonstrated its superiority in image analysis field, and breaks down the dynamic estimation of spin satellites into two sub-problems: target attitude estimation and spin parameters estimation. In this work, the proposed algorithm deduces two explicit expressions of target dynamic parameters under the imaging projection model of the joint optical-and-radar observation. Through the particle swarm optimization (PSO), target dynamic parameters are determined in two stages. This paper presents some experiments illustrating the feasibility of the proposed method and subsequent conclusions, which reflect advantages of the joint optical-and-radar observation mode in image interpretation. [ABSTRACT FROM AUTHOR]

Single image dehazing has been a challenging problem because of its ill-posed nature. For this reason, numerous efforts have been made in the field of haze removal. This paper proposes a simple, fast, and powerful algorithm for haze removal. The medium transmission is derived as a function of the saturation of the scene radiance only, and the saturation of scene radiance is estimated using a simple stretching method. A different medium transmission can be estimated for each pixel because this method does not assume that transmission is constant in a small patch. Furthermore, this paper presents a color veil removing algorithm, which is useful for an image with fine or yellow dust, using the white balance technique. The proposed algorithm requires no training, prior, and refinement process. The simulation results show that the proposed dehazing scheme outperforms state-of-the-art dehazing approaches in terms of both computational complexity and dehazing efficiency. [ABSTRACT FROM AUTHOR]

In this paper, we propose a blind text image deblurring algorithm by using a text-specific hybrid dictionary. After careful analysis, we find that the text-specific hybrid dictionary has the great ability of providing powerful contextual information for text image deblurring. Here, it is worth noting that our proposed method is inspired by our observation that an intermediate latent image contains not only sharp regions, but also multiple types of small blurred regions. Based upon our discovery, we propose a prior for text images based on sparse representation, which models the relationship between an intermediate latent image and a desired sharp image. To this end, we carefully collect three different image patch pairs, which are 1) Gaussian blur-sharp, 2) motion blur-sharp, and 3) sharp-sharp, in order to construct the text-specific hybrid dictionary. We also propose a new optimization framework suitable for the task of text image deblurring in this paper. Extensive experiments have been conducted on a challenging dataset of synthetic and real-world text images. Our results demonstrate that the proposed method outperforms the state-of-the-art image deblurring methods both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Intensity inhomogeneity and noise are two common issues in images but inevitably lead to significant challenges for image segmentation and is particularly pronounced when the two issues simultaneously appear in one image. As a result, most existing level set models yield poor performance when applied to this images. To this end, this paper proposes a novel hybrid level set model, named adaptive variational level set model (AVLSM) by integrating an adaptive scale bias field correction term and a denoising term into one level set framework, which can simultaneously correct the severe inhomogeneous intensity and denoise in segmentation. Specifically, an adaptive scale bias field correction term is first defined to correct the severe inhomogeneous intensity by adaptively adjusting the scale according to the degree of intensity inhomogeneity while segmentation. More importantly, the proposed adaptive scale truncation function in the term is model-agnostic, which can be applied to most off-the-shelf models and improves their performance for image segmentation with severe intensity inhomogeneity. Then, a denoising energy term is constructed based on the variational model, which can remove not only common additive noise but also multiplicative noise often occurred in medical image during segmentation. Finally, by integrating the two proposed energy terms into a variational level set framework, the AVLSM is proposed. The experimental results on synthetic and real images demonstrate the superiority of AVLSM over most state-of-the-art level set models in terms of accuracy, robustness and running time. [ABSTRACT FROM AUTHOR]

Occlusion is an inevitable and critical problem in unsupervised optical flow learning. Existing methods either treat occlusions equally as non-occluded regions or simply remove them to avoid incorrectness. However, the occlusion regions can provide effective information for optical flow learning. In this paper, we present OIFlow, an occlusion-inpainting framework to make full use of occlusion regions. Specifically, a new appearance-flow network is proposed to inpaint occluded flows based on the image content. Moreover, a boundary dilated warp is proposed to deal with occlusions caused by displacement beyond the image border. We conduct experiments on multiple leading flow benchmark datasets such as Flying Chairs, KITTI and MPI-Sintel, which demonstrate that the performance is significantly improved by our proposed occlusion handling framework. [ABSTRACT FROM AUTHOR]

Inferring object-wise human attention in 3D space from the third-person perspective (e.g., a camera) is crucial to many visual tasks and applications, including human-robot collaboration, unmanned vehicle driving, etc. Challenges arise from classical human attention when human eyes are not visible to cameras, gaze point is outside the field of vision, or the gazed object is occluded by others in the 3D space. In this case, blind 3D human attention inference brings a new paradigm to the community. In this paper, we address these challenges by proposing a scene-behavior associated mechanism, in which both 3D scene and temporal behavior of human are adopted to infer object-wise human attention and its transition. Specifically, point cloud is reconstructed and used for the spatial representation of 3D scene, which is beneficial to handle the blind problem from the perspective of a camera. Based on this, in order to address the blind human attention inference without eye information, we propose a Sequential Skeleton Based Attention Network (S2BAN) for behavior-based attention modeling. As is embedded in the scene-behavior associated mechanism, the proposed S2BAN is built under the temporal architecture of Long-Short-Term-Memory (LSTM). Our network employs human skeleton as behavior representation, and maps it to the attention direction frame by frame, which makes attention inference a temporal-correlated issue. With the help of S2BAN, 3D gaze spot and further the attended objects can be obtained frame by frame via intersection and segmentation on the previously reconstructed point cloud. Finally, we conduct experiments from various aspects to verify the object-wise attention localization accuracy, the angular error of attention direction calculation, as well as the subjective results. The experimental results show that the proposed outperforms other competitors. [ABSTRACT FROM AUTHOR]

RGB-Infrared (RGB-IR) cross-modality person re-identification (re-ID) is attracting more and more attention due to requirements for 24-h scene surveillance. However, the high cost of labeling person identities of an RGB-IR dataset largely limits the scalability of supervised models in real-world scenarios. In this paper, we study the unsupervised RGB-IR person re-ID problem (or briefly uRGB-IR re-ID) in which no identity annotations are available in RGB-IR cross-modality datasets. Considering that intra-modality (i.e., RGB-RGB or IR-IR) re-ID is much easier than cross-modality re-ID and can provide shared knowledge for RGB-IR re-ID, we propose a two-stage method to solve the uRGB-IR re-ID, namely homogeneous-to-heterogeneous learning. In the first stage, the unsupervised self-learning method is conducted to learn the intra-modality feature representation and to generate the pseudo-labeled identities of person images separately for each modality. In the second stage, heterogeneous learning is used to learn a shared discriminative feature representation by distilling the knowledge from intra-modality pseudo-labels, to align two modalities via a modality-based consistent learning module, and finally to target modality-invariant learning via a pseudo-labeled positive instance selection module. With the use of homogeneous-to-heterogeneous learning, the proposed unsupervised framework greatly reduces the modality gap and thus learns a robust feature representation against RGB and infrared modalities, leading to promising accuracy. We also propose a novel cross-modality re-ranking approach that includes a self-modality search and a cycle-modality search to tailor the uRGB-IR re-ID. Unlike conventional re-ranking, the proposed re-ranking method takes a modality-based constraint into re-ranking and thus can select more reliable nearest neighbors, which greatly improves uRGB-IR re-ID. The experimental results demonstrate the superiority of our approach on the SYSU-MM01 and RegDB datasets. [ABSTRACT FROM AUTHOR]

Recently, Convolutional Neural Networks (CNNs) have achieved great improvements in blind image motion deblurring. However, most existing image deblurring methods require a large amount of paired training data and fail to maintain satisfactory structural information, which greatly limits their application scope. In this paper, we present an unsupervised image deblurring method based on a multi-adversarial optimized cycle-consistent generative adversarial network (CycleGAN). Although original CycleGAN can handle unpaired training data well, the generated high-resolution images are probable to lose content and structure information. To solve this problem, we utilize a multi-adversarial mechanism based on CycleGAN for blind motion deblurring to generate high-resolution images iteratively. In this multi-adversarial manner, the hidden layers of the generator are gradually supervised, and the implicit refinement is carried out to generate high-resolution images continuously. Meanwhile, we also introduce the structure-aware mechanism to enhance the structure and detail retention ability of the multi-adversarial network for deblurring by taking the edge map as guidance information and adding multi-scale edge constraint functions. Our approach not only avoids the strict need for paired training data and the errors caused by blur kernel estimation, but also maintains the structural information better with multi-adversarial learning and structure-aware mechanism. Comprehensive experiments on several benchmarks have shown that our approach prevails the state-of-the-art methods for blind image motion deblurring. [ABSTRACT FROM AUTHOR]

An image can be decomposed into two parts: the basic content and details, which usually correspond to the low-frequency and high-frequency information of the image. For a hazy image, these two parts are often affected by haze in different levels, e.g., high-frequency parts are often affected more serious than low-frequency parts. In this paper, we approach the single image dehazing problem as two restoration problems of recovering basic content and image details, and propose a Dual-Path Recurrent Network (DPRN) to simultaneously tackle these two problems. Specifically, the core structure of DPRN is a dual-path block, which uses two parallel branches to learn the characteristics of the basic content and details of hazy images. Each branch consists of several Convolutional LSTM blocks and convolution layers. Moreover, a parallel interaction function is incorporated into the dual-path block, thus enables each branch to dynamically fuse the intermediate features of both the basic content and image details. In this way, both branches can benefit from each other, and recover the basic content and image details alternately, therefore alleviating the color distortion problem in the dehazing process. Experimental results show that the proposed DPRN outperforms state-of-the-art image dehazing methods in terms of both quantitative accuracy and qualitative visual effect. [ABSTRACT FROM AUTHOR]

Photometric stereo recovers three-dimensional (3D) object surface normal from multiple images under different illumination directions. Traditional photometric stereo methods suffer from the problem of non-Lambertian surfaces with general reflectance. By leveraging deep neural networks, learning-based methods are capable of improving the surface normal estimation under general non-Lambertian surfaces. These state-of-the-art learning-based methods however do not associate surface normal with reconstructed images and, therefore, they cannot explore the beneficial effect of such association on the estimation of the surface normal. In this paper, we specifically exploit the positive impact of this association and propose a novel dual regression network for both fine surface normals and arbitrary reconstructed images in calibrated photometric stereo. Our work unifies the 3D reconstruction and rendering tasks in a deep learning framework, with the explorations including: 1. generating specified reconstructed images under arbitrary illumination directions, which provides more intuitive perception of the reflectance and is extremely useful for visual applications, such as virtual reality, and 2. our dual regression scheme introduces an additional constraint on observed images and reconstructed images, which forms a closed-loop to provide additional supervision. Experiments show that our proposed method achieves accurate reconstructed images under arbitrarily specified illumination directions and it significantly outperforms the state-of-the-art learning-based single regression methods in calibrated photometric stereo. [ABSTRACT FROM AUTHOR]

Estimating depth and defocus maps are two fundamental tasks in computer vision. Recently, many methods explore these two tasks separately with the help of the powerful feature learning ability of deep learning and these methods have achieved impressive progress. However, due to the difficulty in densely labeling depth and defocus on real images, these methods are mostly based on synthetic training dataset, and the performance of learned network degrades significantly on real images. In this paper, we tackle a new task that jointly estimates depth and defocus from a single image. We design a dual network with two subnets respectively for estimating depth and defocus. The network is jointly trained on synthetic dataset with a physical constraint to enforce the physical consistency between depth and defocus. Moreover, we design a simple method to label depth and defocus order on real image dataset, and design two novel metrics to measure accuracies of depth and defocus estimation on real images. Comprehensive experiments demonstrate that joint training for depth and defocus estimation using physical consistency constraint enables these two subnets to guide each other, and effectively improves their depth and defocus estimation performance on real defocused image dataset. [ABSTRACT FROM AUTHOR]

Existing traditional and ConvNet-based methods for light field depth estimation mainly work on the narrow-baseline scenario. This paper explores the feasibility and capability of ConvNets to estimate depth in another promising scenario: wide-baseline light fields. Due to the deficiency of training samples, a large-scale and diverse synthetic wide-baseline dataset with labelled data is introduced for depth prediction tasks. Considering the practical goal for real-world applications, we design an end-to-end trained lightweight convolutional network to infer depths from light fields, called LLF-Net. The proposed LLF-Net is built by incorporating a cost volume which allows variable angular light field inputs and an attention module that enables to recover details at occlusion areas. Evaluations are made on the synthetic and real-world wide-baseline light fields, and experimental results show that the proposed network achieves the best performance when compared to recent state-of-the-art methods. We also evaluate our LLF-Net on narrow-baseline datasets, and it consequently improves the performance of previous methods. [ABSTRACT FROM AUTHOR]

This paper proposes a regularized blind deconvolution method for restoring Poissonian blurred image. The problem is formulated by utilizing the ${L}_{0}$ -norm of image gradients and total variation (TV) to regularize the latent image and point spread function (PSF), respectively, and combining them with the negative logarithmic Poisson log-likelihood. To solve the problem, we propose an approach which combines the methods of variable splitting and Lagrange multiplier to convert the original problem into three sub-problems, and then design an alternating minimization algorithm which incorporates the estimation of PSF and latent image as well as the updation of Lagrange multiplier into account. We also design a non-blind deconvolution method based on TV regularization to further improve the quality of the restored image. Experimental results on both synthetic and real-world Poissonian blurred images show that the proposed method can achieve restored images of very high quality, which is competitive with or even better than some state of the art methods. [ABSTRACT FROM AUTHOR]

For a procam to preserve the color appearance of an image projected on a color surface, the photometric distortion introduced by the color surface has to be properly compensated. The performance of such photometric compensation relies on an accurate estimation of the projector nonlinearity. In this paper, we improve the accuracy of projector nonlinearity estimation by taking inter-pixel coupling into consideration. In addition, to respond quickly to the change of projection area due to projector movement, we reduce the number of calibration patterns from six to one and use the projected image as the calibration pattern. This greatly improves the computational efficiency of re-calibration that needs to be performed on the fly during a multimedia presentation without breaking its continuity. Both objective and subjective results are provided to illustrate the effectiveness of the proposed method for color compensation. [ABSTRACT FROM AUTHOR]

The human visual system (HVS) is a hierarchical system, in which visual signals are processed hierarchically. In this paper, the HVS is modeled as a three-level communication system and visual perception is divided into three stages according to the hierarchical predictive coding theory. Then, a novel just noticeable distortion (JND) estimation scheme is proposed. In visual perception, the input signals are predicted constantly and spontaneously in each hierarchy, and neural response is evoked by the central residue and inhibited by surrounding residues. These two types’ residues are regarded as the positive and negative visual incentives which cause positive and negative perception effects, respectively. In neuroscience, the effect of incentive on observer is measured by the surprise of this incentive. Thus, we propose a surprise-based measurement method to measure both perception effects. Specifically, considering the biased competition of visual attention, we define the product of the residue self-information (i.e., surprise) and the competition biases as the perceptual surprise to measure the positive perception effect. As for the negative perception effect, it is measured by the average surprise (i.e., the local Shannon entropy). The JND threshold of each stage is estimated individually by considering both perception effects. The total JND threshold is finally obtained by non-linear superposition of three stage thresholds. Furthermore, the proposed JND estimation scheme is incorporated into the codec of Versatile Video Coding for image compression. Experimental results show that the proposed JND model outperforms the relevant existing ones, and over 16% of bit rate can be reduced without jeopardizing the perceptual quality. [ABSTRACT FROM AUTHOR]

Existing RGB-D salient object detection methods treat depth information as an independent component to complement RGB and widely follow the bistream parallel network architecture. To selectively fuse the CNN features extracted from both RGB and depth as a final result, the state-of-the-art (SOTA) bistream networks usually consist of two independent subbranches: one subbranch is used for RGB saliency, and the other aims for depth saliency. However, depth saliency is persistently inferior to the RGB saliency because the RGB component is intrinsically more informative than the depth component. The bistream architecture easily biases its subsequent fusion procedure to the RGB subbranch, leading to a performance bottleneck. In this paper, we propose a novel data-level recombination strategy to fuse RGB with D (depth) before deep feature extraction, where we cyclically convert the original 4-dimensional RGB-D into DGB, RDB and RGD. Then, a newly lightweight designed triple-stream network is applied over these novel formulated data to achieve an optimal channel-wise complementary fusion status between the RGB and D, achieving a new SOTA performance. [ABSTRACT FROM AUTHOR]

We present an approach to extend the functionality and the use of kernel machines in image processing applications. We introduce a novel way to design spatial kernel machines with spatial properties and demonstrate how those newly introduced spatial properties enhance the possibilities of the use of kernel machines in image processing applications as a proof of concept. In this paper, we demonstrate four particular extensions: 1) how to model shapes efficiently with spatially computed kernel parameters in a geometrically scalable way; 2) how to visualize the kernel parameters precisely and intuitively on binary 2D shapes; 3) how to construct a one-class classifier from the binary classifier in a straightforward manner without re-training; and 4) how to use the computed kernel parameters for filtering. The existing literature on kernel machines mostly focuses on estimating the optimal kernel parameters via additional cost function(s). In this paper, instead of employing an additional cost function to estimate the kernel-related parameters, we investigate on an analytical solution to predict the actual kernel parameters locally and show how to build a spatial kernel machine with our analytical approach. Classical kernel machines do not perform well on precise shape modeling with a low number of support vectors as demonstrated in this paper. However, we demonstrate and visualize that our analytical approach provides a natural means to relate the kernel parameters to the 2D shapes for sparse shape modeling, where the shape boundary represents the decision boundary. For that, we incorporate the selected kernel function’s geometric properties as an additional constraint into the classifier’s optimization problem by defining an easy-to-explain and intuitive concept: similarity domains. In our experiments, we study and demonstrate how the resulting new kernel machine enhances the capabilities of the classical kernel machines with applications on shape modeling, (geometrically) scaling the non-linear decision boundary at various scales and precise visualization of the kernel parameters in 2D images. [ABSTRACT FROM AUTHOR]

In this paper, we propose an image completion algorithm based on dense correspondence between the input image and an exemplar image retrieved from the Internet. Contrary to traditional methods which register two images according to sparse correspondence, in this paper, we propose a hierarchical PatchMatch method that progressively estimates a dense correspondence, which is able to capture small deformations between images. The estimated dense correspondence has usually large occlusion areas that correspond to the regions to be completed. A nearest neighbor field (NNF) interpolation algorithm interpolates a smooth and accurate NNF over the occluded region. Given the calculated NNF, the correct image content from the exemplar image is transferred to the input image. Finally, as there could be a color difference between the completed content and the input image, a color correction algorithm is applied to remove the visual artifacts. Numerical results show that our proposed image completion method can achieve photo realistic image completion results. [ABSTRACT FROM AUTHOR]

In this paper, we propose an effective approach to infer the just noticeable distortion (JND) profile based on patch-level structural visibility learning. Instead of pixel-level JND profile estimation, the image patch, which is regarded as the basic processing unit to better correlate with the human perception, can be further decomposed into three conceptually independent components for visibility estimation. In particular, to incorporate the structural degradation into the patch-level JND model, a deep learning-based structural degradation estimation model is trained to approximate the masking of structural visibility. In order to facilitate the learning process, a JND dataset is further established, including 202 pristine images and 7878 distorted images generated by advanced compression algorithms based on the upcoming Versatile Video Coding (VVC) standard. Extensive experimental results further show the superiority of the proposed approach over the state-of-the-art. Our dataset is available at: https://github.com/ShenXuelin-CityU/PWJNDInfer. [ABSTRACT FROM AUTHOR]

Mobile devices usually mount a depth sensor to resolve ill-posed problems, like salient object detection on cluttered background. The main barrier of exploring RGBD data is to handle the information from two different modalities. To cope with this problem, in this paper, we propose a boundary-aware cross-modal fusion network for RGBD salient object detection. In particular, to enhance the fusion of color and depth features, we present a cross-modal feature sampling module to balance the contribution of the RGB and depth features based on the statistics of their channel values. In addition, in our multi-scale dense fusion network architecture, we not only incorporate edge-sensitive losses to preserve the boundary of the detected salient region, but also refine its structure by merging the estimated saliency maps of different scales. We accomplish the multi-scale saliency map merging using two alternative methods which produce refined saliency maps via per-pixel weighted combination and an encoder-decoder network. Extensive experimental evaluations demonstrate that our proposed framework can achieve the state-of-the-art performance on several public RGBD-based datasets. [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]

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]

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]

Albeit remarkable progress has been made to improve the accuracy and completeness of multi-view stereo (MVS), existing methods still suffer from either sparse reconstructions of low-textured surfaces or heavy computational burden. In this paper, we propose a Confidence-based Large-scale Dense Multi-view Stereo (CLD-MVS) method for high resolution imagery. Firstly, we formulate MVS as a multi-view depth estimation problem, and employ a normal-aware efficient PatchMatch stereo to estimate the initial depth and normal map for each reference view. A self-supervised deep learning method is then developed to predict the spatial confidence for multi-view depth maps, which is combined with cross-view consistency to generate the ground control points. Subsequently, a confidence-driven and boundary-aware interpolation scheme using static and dynamic guidance is adopted to synthesize dense depth and normal maps. Finally, a refinement procedure which leverages synthesized depth and normal as prior is conducted to estimate cross-view consistent surface. Experiments show that the proposed CLD-MVS method achieves high geometric completeness while preserving fine-scale details. In particular, it has ranked No. 1 on the ETH3D high-resolution MVS benchmark in terms of $F_{1}$ -score. [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]

Accurate depth estimation from images is a fundamental problem in computer vision. In this paper, we propose an unsupervised learning based method to predict high-quality depth map from multiple images. A novel multi-view constrained DenseDepthNet is designed for this task. Our DenseDepthNet can effectively leverage both the low-level and high-level features of input images and generate appealing results, especially with sharp details. We employ the public datasets KITTI and Cityscapes for training in an end-to-end unsupervised fashion. A novel depth consistency loss based on multi-view geometry constraint is also applied to the corresponding points across pairwise images, which helps to improve the quality of predicted depth maps significantly. We conduct comprehensive evaluations on our DenseDepthNet and our depth consistency loss function. Experiments validate that our method outperforms the state-of-the-art unsupervised methods and produce comparable results with supervised methods. [ABSTRACT FROM AUTHOR]

Both structural and contextual information is essential and widely used in image analysis. However, current multi-view stereo (MVS) approaches usually use a single common pre-trained model as pixel descriptor to extract features, which mix structural and contextual information together and thus increase the difficulty of matching correspondence. In this paper, we propose FADE (feature aggregation for depth estimation), which treats spatial and context information separately and focuses on aggregating features for efficient learning of the MVS problem. Spatial information includes image details such as edges and corners, whereas context information comprises object features such as shapes and traits. To aggregate these multi-level features, we use an attention mechanism to select important features for matching. We then build a plane sweep volume by using a homography backward warping method to generate match candidates. Furthermore, we propose a novel cost volume regularization network aims to minimize the noise in the matching candidates. Finally, we take advantage of 3D stacked hourglass and regression to produces high-quality depth maps. With these well-aggregated features, FADE can efficiently perform dense depth reconstruction, achieving state-of-the-art performance in terms of accuracy and requiring the least amount of model parameters. [ABSTRACT FROM AUTHOR]

Recently, the end-to-end learning-based methods have been proven effective for the blind image deblurring. Without human-made assumptions or numerical algorithms, they are able to restore images with fewer artifacts and better perceptual quality. However, in practice, these methods suffer from limited performance under complex motion scenario and produces unnatural results sometimes. In this paper, in order to overcome their limitations, we propose to integrate deep convolution neural networks into a conventional deblurring framework. Specifically, we propose Stacked Estimation Residual Net (SEN) to estimate the motion flow map and Recurrent Prior Generative and Adversarial Net (RP-GAN) to learn the implicit image prior for the optimization. Comparing with the state-of-the-art end-to-end learning-based methods, the proposed method restores image content more naturally and shows better generalization ability. [ABSTRACT FROM AUTHOR]

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

Existing two-dimensional (2D) autofocus algorithms, exploiting the known structure of 2D phase error, lack the error estimation accuracy in the case of a low signal-to-noise ratio (SNR) due to the non-exhaustive use of the echo signal. In this paper, we propose a novel 2D autofocus algorithm, thoroughly utilizing all the available data and therefore achieving superior estimation performance. Via analytical study, we show that the partial derivative of the 2D error with respect to the azimuth frequency is approximable as a function of single argument, after appropriate change of variable. The established property enables a scheme for the azimuth phase error (APE) measurement, where the polar formatted data are fragmented along the range frequency and then aligned along the azimuth frequency, in order to equalize phase gradients in different fragments. On the one hand, such a scheme avoids the necessity to divide the full-aperture signal into subapertures, while on the other hand, it involves the whole signal support. Improved accuracy of the resulting estimate is achieved through the joint inter-fragment estimation of the APE gradient. The proposed algorithm, based on the mentioned scheme, was validated via computer simulations. The conducted experiments confirmed its preference against the existing techniques. The preference is particularly distinct for low SNR imagery. [ABSTRACT FROM AUTHOR]

Current non-Lambertian photometric stereo methods generally require a large number of images to ensure accurate surface normal estimation. To achieve accurate surface normal recovery under a sparse set of lights, this paper proposes a non-Lambertian photometric stereo network based on a derived inverse reflectance model with collocated light. The model is deduced using monotonicity of isotropic reflectance and the univariate property of collocated light to decouple the surface normal from the reflectance function. Thus, the surface normal can be estimated by three steps, i.e., model fitting, shadow rejection, and normal estimation. We leverage a supervised deep learning technique to enhance the shadow rejection ability and the flexibility of the inverse reflectance model. Shadows are handled through max-pooling. Information from a neighborhood image patch is utilized to improve the flexibility to various reflectances. Experiments using both synthetic and real images demonstrate that the proposed method achieves state-of-the-art accuracy in surface normal estimation. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation for indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small number of (e.g., 3~5) color images from uncalibrated sparse views, which significantly simplifies data acquisition and broadens applicable scenarios. To achieve promising 3D reconstruction from sparse views with limited overlap, our method first recovers the depth map and semantic information for each view, and then fuses the depth maps into a 3D scene. To this end, we design an iterative deep architecture, named IterNet, to estimate the depth map and semantic segmentation alternately. To obtain accurate alignment between views with limited overlap, we further propose a joint global and local registration method to reconstruct a 3D scene with semantic information. We also make available a new indoor synthetic dataset, containing photorealistic high-resolution RGB images, accurate depth maps and pixel-level semantic labels for thousands of complex layouts. Experimental results on public datasets and our dataset demonstrate that our method achieves more accurate depth estimation, smaller semantic segmentation errors, and better 3D reconstruction results over state-of-the-art methods. [ABSTRACT FROM AUTHOR]