Seamlessly moving objects within a scene is a common requirement for image editing, but it is still a challenge for existing editing methods. Especially for real-world images, the occlusion situation further increases the difficulty. The main difficulty is that the occluded portion needs to be completed before movement can proceed. To leverage the real-world knowledge embedded in the pre-trained diffusion models, we propose a Diffusion-based framework specifically designed for Occluded Object Movement, named DiffOOM. The proposed DiffOOM consists of two parallel branches that perform object de-occlusion and movement simultaneously. The de-occlusion branch utilizes a background color-fill strategy and a continuously updated object mask to focus the diffusion process on completing the obscured portion of the target object. Concurrently, the movement branch employs latent optimization to place the completed object in the target location and adopts local text-conditioned guidance to integrate the object into new surroundings appropriately. Extensive evaluations across various metrics demonstrate the superior performance of our method, which is further validated by a comprehensive user study.

Large-scale pre-trained diffusion models are becoming increasingly popular in solving the Real-World Image Super-Resolution (Real-ISR) problem because of their rich generative priors. The recent development of diffusion transformer (DiT) has witnessed overwhelming performance over the traditional UNet-based architecture in image generation, which also raises the question: Can we adopt the advanced DiT-based diffusion model for Real-ISR? To this end, we propose our DiT4SR, one of the pioneering works to tame the large-scale DiT model for Real-ISR. Instead of directly injecting embeddings extracted from low-resolution (LR) images like ControlNet, we integrate the LR embeddings into the original attention mechanism of DiT, allowing for the bidirectional flow of information between the LR latent and the generated latent. The sufficient interaction of these two streams allows the LR stream to evolve with the diffusion process, producing progressively refined guidance that better aligns with the generated latent at each diffusion step. Additionally, the LR guidance is injected into the generated latent via a cross-stream convolution layer, compensating for DiT's limited ability to capture local information. These simple but effective designs endow the DiT model with superior performance in Real-ISR, which is demonstrated by extensive experiments. Project Page: https://adam-duan.github.io/projects/dit4sr/.

Diffusion models have achieved significant progress in image generation and the pre-trained Stable Diffusion (SD) models are helpful for image deblurring by providing clear image priors. However, directly using a blurry image or a pre-deblurred one as a conditional control for SD will either hinder accurate structure extraction or make the results overly dependent on the deblurring network. In this work, we propose a Latent Kernel Prediction Network (LKPN) to achieve robust real-world image deblurring. Specifically, we co-train the LKPN in the latent space with conditional diffusion. The LKPN learns a spatially variant kernel to guide the restoration of sharp images in the latent space. By applying element-wise adaptive convolution (EAC), the learned kernel is utilized to adaptively process the blurry feature, effectively preserving the information of the blurry input. This process thereby more effectively guides the generative process of SD, enhancing both the deblurring efficacy and the quality of detail reconstruction. Moreover, the results at each diffusion step are utilized to iteratively estimate the kernels in LKPN to better restore the sharp latent by EAC in the subsequent step. This iterative refinement enhances the accuracy and robustness of the deblurring process. Extensive experimental results demonstrate that the proposed method outperforms state-of-the-art image deblurring methods on both benchmark and real-world images.

Contemporary display enables video content rendering with high dynamic range (HDR) and wide color gamut (WCG). However, the majority of existing content remains in standard dynamic range (SDR) format. Therefore, the conversion of SDR content to HDRTV standards holds significant value. This paper delineates and analyzes the SDRTV-to-HDRTV conversion by modeling the formation of SDRTV/HDRTV content. The findings reveal that a naive end-to-end supervised training pipeline suffers from severe gamut transition errors. To address this, we propose a new three-step solution called HDRTVNet++, which includes adaptive global color mapping, local enhancement, and highlight refinement. The adaptive global color mapping step utilizes global statistics for image-adaptive color adjustments, followed by a local enhancement network for detail improvement. These two components are integrated as a generator, with GAN-based joint training ensuring highlight consistency. Our method, tailored for ultra-high-definition TV content, offers both effectiveness and computational efficiency in processing 4K resolution images. We also construct HDRTV1K, a dataset comprising HDR videos adhering to the HDR10 standard, featuring 1235 training and 117 testing images at 4K resolution. Furthermore, we employ five metrics to assess SDRTV-to-HDRTV performance. Our results demonstrate state-of-the-art performance both quantitatively and visually. The codes and models are available athttps://github.com/xiaom233/HDRTVNet-plus.

Deep image restoration models aim to learn a mapping from degraded image space to natural image space. However, they face several critical challenges: removing degradation, generating realistic details, and ensuring pixel-level consistency. Over time, three major classes of methods have emerged, including MSE-based, GAN-based, and diffusion-based methods. However, they fail to achieve a good balance between restoration quality, fidelity, and speed. We propose a novel method, HYPIR, to address these challenges. Our solution pipeline is straightforward: it involves initializing the image restoration model with a pre-trained diffusion model and then fine-tuning it with adversarial training. This approach does not rely on diffusion loss, iterative sampling, or additional adapters. We theoretically demonstrate that initializing adversarial training from a pre-trained diffusion model positions the initial restoration model very close to the natural image distribution. Consequently, this initialization improves numerical stability, avoids mode collapse, and substantially accelerates the convergence of adversarial training. Moreover, HYPIR inherits the capabilities of diffusion models with rich user control, enabling text-guided restoration and adjustable texture richness. Requiring only a single forward pass, it achieves faster convergence and inference speed than diffusion-based methods. Extensive experiments show that HYPIR outperforms previous state-of-the-art methods, achieving efficient and high-quality image restoration.

Event cameras, with their high temporal resolution, dynamic range, and low power consumption, are particu-larly good at time-sensitive applications like deblurring and frame interpolation. However, their performance is hindered by latency variability, especially under low-light conditions and with fast-moving objects. This paper addresses the challenge of latency in event cameras - the temporal discrepancy between the actual occurrence of changes in the corresponding timestamp assigned by the sensor. Focusing on event-guided deblurring and frame interpolation tasks, we propose a latency correction method based on a parameterized latency model. To enable data-driven learning, we develop an event-based temporal fidelity to describe the sharpness of latent images reconstructed from events and the corresponding blurry images, and reformulate the event-based double integral model differentiable to latency. The proposed method is validated using synthetic and real-world datasets, demonstrating the benefits of latency correction for deblurring and interpolation across different lighting conditions.

Neuromorphic event sensors are novel visual cameras that feature high-speed illumination-variation sensing and have found widespread application in guiding frame-based imaging enhancement. This paper focuses on color restoration in the event-guided image deblurring task, we fuse blurry images with mosaic color events instead of mono events to avoid artifacts such as color bleeding. The challenges associated with this approach include demosaicing color events for reconstructing full-resolution sampled signals and fusing bimodal signals to achieve image deblurring. To meet these challenges, we propose a novel network called Color4E to enhance the color restoration quality for the image deblurring task. Color4E leverages an event demosaicing module to upsample the spatial resolution of mosaic color events and a cross-encoding image deblurring module for fusing bimodal signals, a refinement module is designed to fuse full-color events and refine initial deblurred images. Furthermore, to avoid the real-simulated gap of events, we implement a display-filter-camera system that enables mosaic and full-color event data captured synchronously, to collect a real-captured dataset used for network training and validation. The results on the public dataset and our collected dataset show that Color4E enables high-quality event-based image deblurring compared to state-of-the-art methods.

Event streams provide a novel paradigm to describe visual scenes by capturing intensity variations above specific thresholds along with various types of noise. Existing event generation methods usually rely on one-way mappings using hand-crafted parameters and noise rates, which may not adequately suit diverse scenarios and event cameras. To address this limitation, we propose a novel approach to learn a bidirectional mapping between the feature space of event streams and their inherent parameters, enabling the generation of reliable event streams with enhanced generalization capabilities. We first randomly generate a vast number of parameters and synthesize massive event streams using an event simulator. Subsequently, an event-based normalizing flow network is proposed to learn the invertible mapping between the representation of a synthetic event stream and its parameters. The invertible mapping is implemented by incorporating an intensity-guided conditional affine simulation mechanism, facilitating better alignment between event features and parameter spaces. Additionally, we impose constraints on event sparsity, edge distribution, and noise distribution through novel event losses, further emphasizing event priors in the bidirectional mapping. Our framework surpasses state-of-the-art methods in video reconstruction, optical flow estimation, and parameter estimation tasks on synthetic and real-world datasets, exhibiting excellent generalization across diverse scenes and cameras.

Continuous-time video frame interpolation is a fundamental technique in computer vision for its flexibility in synthesizing motion trajectories and novel video frames at arbitrary intermediate time steps. Yet, how to infer accurate intermediate motion and synthesize high-quality video frames are two critical challenges. In this paper, we present a novel VFI framework with improved treatment for these challenges. To address the former, we propose focalized trajectory fitting, which performs confidence-aware motion trajectory estimation by learning to pay focus to reliable optical flow candidates while suppressing the outliers. The second is range-nullspace synthesis, a novel frame renderer cast as solving an ill-posed problem addressed by learning decoupled components in orthogonal subspaces. The proposed framework sets new records on 7 of 10 public VFI benchmarks.

In this study, we introduce a challenging task called Joint Demosaicking and Denoising in Quad Bayer CFA (JDD-QBC). Inspired by the effectiveness of gradient prior in previous tasks, we design a gradient prior extraction algorithm to extract robust gradient profiles directly from Quad Bayer raw images. By leveraging contextual information, our algorithm overcomes the limitations of previous gradient extraction algorithms. Building on this prior, we propose an end-to-end JDD-QBC framework called Gradient Guidance Network (G2-Net), consisting of two specifically designed components: a Gradient Refinement Branch (GRB) to transform the extracted gradient prior, and a Multi-Scale Backbone Branch (MSB2) to recover all missing values under the guidance of transformed prior. Extensive experiments demonstrate our proposed G2-Net outperforms state-of-the-art methods across a wide range of noise levels while requiring 50% less memory cost.

Imaging is usually a mixture problem of incomplete color sampling, noise degradation, and limited resolution. This mixture problem is typically solved by a sequential solution that applies demosaicing (DM), denoising (DN), and super-resolution (SR) sequentially in a fixed and predefined pipeline (execution order of tasks), DM→DN→SR. The most recent work on image processing focuses on developing more sophisticated architectures to achieve higher image quality. Little attention has been paid to the design of the pipeline, and it is still not clear how significant the pipeline is to image quality. In this work, we comprehensively study the effects of pipelines on the mixture problem of learning-based DN, DM, and SR, in both sequential and joint solutions. On the one hand, in sequential solutions, we find that the pipeline has a non-trivial effect on the resulted image quality. Our suggested pipeline DN→SR→DM yields consistently better performance than other sequential pipelines in various experimental settings and benchmarks. On the other hand, in joint solutions, we propose an end-to-end Trinity Pixel Enhancement NETwork (TENet) that achieves the state-of-the-art performance for the mixture problem. We further present a novel and simple method that can integrate a certain pipeline into a given end-to-end network by providing intermediate supervision using a detachable head. Extensive experiments show that an end-to-end network with the proposed pipeline can attain only a consistent but insignificant improvement. Our work indicates that the investigation of pipelines is applicable in sequential solutions, but is not very necessary in end-to-end networks.

Joint filtering mainly uses an additional guidance image as a prior and transfers its structures to the target image in the filtering process. Different from existing approaches that rely on local linear models or hand-designed objective functions to extract the structural information from the guidance image, we propose a new joint filtering method based on a spatially variant linear representation model (SVLRM), where the target image is linearly represented by the guidance image. However, learning SVLRMs for vision tasks is a highly ill-posed problem. To estimate the spatially variant linear representation coefficients, we develop an effective approach based on a deep convolutional neural network (CNN). As such, the proposed deep CNN (constrained by the SVLRM) is able to model the structural information of both the guidance and input images. We show that the proposed approach can be effectively applied to a variety of applications, including depth/RGB image upsampling and restoration, flash deblurring, natural image denoising, and scale-aware filtering. In addition, we show that the linear representation model can be extended to high-order representation models (e.g., quadratic and cubic polynomial representations). Extensive experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods that have been specifically designed for each task.

Deblurring images captured in dynamic scenes is challenging as the motion blurs are spatially varying caused by camera shakes and object movements. In this paper, we propose a spatially varying neural network to deblur dynamic scenes. The proposed model is composed of three deep convolutional neural networks (CNNs) and a recurrent neural network (RNN). The RNN is used as a deconvolution operator on feature maps extracted from the input image by one of the CNNs. Another CNN is used to learn the spatially varying weights for the RNN. As a result, the RNN is spatial-aware and can implicitly model the deblurring process with spatially varying kernels. To better exploit properties of the spatially varying RNN, we develop both one-dimensional and two-dimensional RNNs for deblurring. The third component, based on a CNN, reconstructs the final deblurred feature maps into a restored image. In addition, the whole network is end-to-end trainable. Quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method performs favorably against the state-of-the-art deblurring algorithms.

Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as tracking. However, removing dynamic scene blur from images is a non-trivial task as it is difficult to model the non-uniform blur mathematically. Several methods first use single or multiple images to estimate optical flow (which is treated as an approximation of blur kernels) and then adopt non-blind deblurring algorithms to reconstruct the sharp images. However, these methods cannot be trained in an end-to-end manner and are usually computationally expensive. In this paper, we explore optical flow to remove dynamic scene blur by using the multi-scale spatially variant recurrent neural network (RNN). We utilize FlowNets to estimate optical flow from two consecutive images in different scales. The estimated optical flow provides the RNN weights in different scales so that the weights can better help RNNs to remove blur in the feature spaces. Finally, we develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features. Both quantitatively and qualitatively evaluations on the benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of accuracy, speed, and model size.

Deep neural networks have been widely used in image denoising during the past few years. Even though they achieve great success on this problem, they are computationally inefficient which makes them inappropriate to be implemented in mobile devices. In this paper, we propose an efficient deep neural network for image denoising based on pixel-wise classification. Despite using a computationally efficient network cannot effectively remove the noises from any content, it is still capable to denoise from a specific type of pattern or texture. The proposed method follows such a divide and conquer scheme. We first use an efficient U-net to pixel-wisely classify pixels in the noisy image based on the local gradient statistics.Then we replace part of the convolution layers in existing denoising networks by the proposed Class Specific Convolution layers (CSConv) which use different weights for different classes of pixels. Quantitative and qualitative evaluations on public datasets demonstrate that the proposed method can reduce the computational costs without sacrificing the performance compared to state-of-the-art algorithms.

Blind deblurring has received considerable attention in recent years. However, state-of-the-art methods often fail to process saturated blurry images. The main reason is that pixels around saturated regions are not conforming to the commonly used linear blur model. Pioneer arts suggest excluding these pixels during the deblurring process, which sometimes simultaneously removes the informative edges around saturated regions and results in insufficient information for kernel estimation when large saturated regions exist. To address this problem, we introduce a new blur model to fit both saturated and unsaturated pixels, and all informative pixels can be considered during the deblurring process. Based on our model, we develop an effective maximum a posterior (MAP)-based optimization framework. Quantitative and qualitative evaluations on benchmark datasets and challenging real-world examples show that the proposed method performs favorably against existing methods.

Deblurring night blurry images is difficult, because the common-used blur model based on the linear convolution operation does not hold in this situation due to the influence of saturated pixels. In this paper, we propose a non-blind deblurring network (NBDN) to restore night blurry images. To mitigate the side effects brought by the pixels that violate the blur model, we develop a confidence estimation unit (CEU) to estimate a map which ensures smaller contributions of these pixels in the deconvolution steps which are optimized by the conjugate gradient (CG) method. Moreover, unlike the existing methods using manually tuned hyper-parameters in their frameworks, we propose a hyper-parameter estimation unit (HPEU) to adaptively estimate hyper-parameters for better image restoration. The experimental results demonstrate that the proposed network performs favorably against state-of-the-art algorithms both quantitatively and qualitatively.

Nowadays modern displays are capable to render video content with high dynamic range (HDR) and wide color gamut (WCG). However, most available resources are still in standard dynamic range (SDR). Therefore, there is an urgent demand to transform existing SDR-TV contents into their HDR-TV versions. In this paper, we conduct an analysis of SDRTV-to-HDRTV task by modeling the formation of SDRTV/HDRTV content. Base on the analysis, we propose a three-step solution pipeline including adaptive global color mapping, local enhancement and highlight generation. Moreover, the above analysis inspires us to present a lightweight network that utilizes global statistics as guidance to conduct image-adaptive color mapping. In addition, we construct a dataset using HDR videos in HDR10 standard, named HDRTV1K, and select five metrics to evaluate the results of SDRTV-to-HDRTV algorithms. Furthermore, our final results achieve state-of-the-art performance in quantitative comparisons and visual quality. The code and dataset are available at https://github.com/chxy95/HDRTVNet.

Recently, video deblurring has attracted considerable research attention, and several works suggest that events at high time rate can benefit deblurring. Existing video deblurring methods assume consecutively blurry frames, while neglecting the fact that sharp frames usually appear nearby blurry frame. In this paper, we develop a principled framework D2Nets for video deblurring to exploit non-consecutively blurry frames, and propose a flexible event fusion module (EFM) to bridge the gap between event-driven and video deblurring. In D2Nets, we propose to first detect nearest sharp frames (NSFs) using a bidirectional LST-M detector, and then perform deblurring guided by NSFs. Furthermore, the proposed EFM is flexible to be incorporated into D2Nets, in which events can be leveraged to notably boost the deblurring performance. EFM can also be easily incorporated into existing deblurring networks, making event-driven deblurring task benefit from state-of-the-art deblurring methods. On synthetic and real-world blurry datasets, our methods achieve better results than competing methods, and EFM not only benefits D2Nets but also significantly improves the competing deblurring networks.

Event-based video frame interpolation is promising as event cameras capture dense motion signals that can greatly facilitate motion-aware synthesis. However, training existing frameworks for this task requires high frame-rate videos with synchronized events, posing challenges to collect real training data. In this work we show event-based frame interpolation can be trained without the need of high frame-rate videos. This is achieved via a novel weakly supervised framework that 1) corrects image appearance by extracting complementary information from events and 2) supplants motion dynamics modeling with attention mechanisms. For the latter we propose subpixel attention learning, which supports searching high-resolution correspondence efficiently on low-resolution feature grid. Though trained on low frame-rate videos, our framework outperforms existing models trained with full high frame-rate videos (and events) on both GoPro dataset and a new real event-based dataset. Codes, models and dataset will be made available at: https://github.com/YU-Zhiyang/WEVI.

Low-dose CT has been a key diagnostic imaging modality to reduce the potential risk of radiation overdose to patient health. Despite recent advances, CNN-based approaches typically apply filters in a spatially invariant way and adopt similar pixel-level losses, which treat all regions of the CT image equally and can be inefficient when fine-grained structures coexist with non-uniformly distributed noises. To address this issue, we propose a Structure-preserving Kernel Prediction Network (StructKPN) that combines the kernel prediction network with a structure-aware loss function that utilizes the pixel gradient statistics and guides the model towards spatially-variant filters that enhance noise removal, prevent over-smoothing and preserve detailed structures for different regions in CT imaging. Extensive experiments demonstrated that our approach achieved superior performance on both synthetic and non-synthetic datasets, and better preserves structures that are highly desired in clinical screening and low-dose protocol optimization.

We present an algorithm to directly solve numerous image restoration problems (e.g., image deblurring, image dehazing, and image deraining). These problems are ill-posed, and the common assumptions for existing methods are usually based on heuristic image priors. In this paper, we show that these problems can be solved by generative models with adversarial learning. However, a straightforward formulation based on a straightforward generative adversarial network (GAN) does not perform well in these tasks, and some structures of the estimated images are usually not preserved well. Motivated by an interesting observation that the estimated results should be consistent with the observed inputs under the physics models, we propose an algorithm that guides the estimation process of a specific task within the GAN framework. The proposed model is trained in an end-to-end fashion and can be applied to a variety of image restoration and low-level vision problems. Extensive experiments demonstrate that the proposed method performs favorably against state-of-the-art algorithms.

The success of existing face deblurring methods based on deep neural networks is mainly due to the large model capacity. Few algorithms have been specially designed according to the domain knowledge of face images and the physical properties of the deblurring process. In this paper, we propose an effective face deblurring algorithm based on deep convolutional neural networks (CNNs). Motivated by the conventional deblurring process which usually involves the motion blur estimation and the latent clear image restoration, the proposed algorithm first estimates motion blur by a deep CNN and then restores latent clear images with the estimated motion blur. However, estimating motion blur from blurry face images is difficult as the textures of the blurry face images are scarce. As most face images share some common global structures which can be modeled well by sketch information, we propose to learn face sketches by a deep CNN so that the sketches can help the motion blur estimation. With the estimated motion blur, we then develop an effective latent image restoration algorithm based on a deep CNN. Although involving the several components, the proposed algorithm is trained in an end-to-end fashion. We analyze the effectiveness of each component on face image deblurring and show that the proposed algorithm is able to deblur face images with favorable performance against state-of-the-art methods.

We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution. The proposed algorithm first uses a deep neural network to estimate intermediate high-resolution images, blurs the intermediate images using known blur kernels, and then substitutes values of the pixels at the un-decimated positions with those of the corresponding pixels from the low-resolution images. The output of the pixel substitution process strictly satisfies the image formation model and is further refined by the same deep neural network in a cascaded manner. The proposed framework is trained in an end-to-end fashion and can work with existing feed-forward deep neural networks for super-resolution and converges fast in practice. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.

Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process. For event-based cameras, however, fast motion can be captured as events at high frame rate, raising new opportunities to exploring effective solutions. In this paper, we start from a sequential formulation of event-based motion deblurring, then show how its optimization can be unfolded with a novel end-toend deep architecture. The proposed architecture is a convolutional recurrent neural network that integrates visual and temporal knowledge of both global and local scales in principled manner. To further improve the reconstruction, we propose a differentiable directional event filtering module to effectively extract rich boundary prior from the evolution of events. We conduct extensive experiments on the synthetic GoPro dataset and a large newly introduced dataset captured by a DAVIS240C camera. The proposed approach achieves state-of-the-art reconstruction quality, and generalizes better to handling real-world motion blur.

Understanding of human vision system (HVS) has inspired many computer vision algorithms. Stereo matching, which borrows the idea from human stereopsis, has been extensively studied in the existing literature. However, scant attention has been drawn on a typical scenario where binocular inputs are qualitatively different (e.g., high-res master camera and low-res slave camera in a dual-lens module). Recent advances in human optometry reveal the capability of the human visual system to maintain coarse stereopsis under such visually imbalanced conditions. Bionically aroused, it is natural to question that: do stereo machines share the same capability? In this paper, we carry out a systematic comparison to investigate the effect of various imbalanced conditions on current popular stereo matching algorithms. We show that resembling the human visual system, those algorithms can handle limited degrees of monocular downgrading but also prone to collapses beyond a certain threshold. To avoid such collapse, we propose a solution to recover the stereopsis by a joint guided-view-restoration and stereo-reconstruction framework. We show the superiority of our framework on KITTI dataset and its extension on real-world applications.

Automatically selecting exposure bracketing (images exposed differently) is important to obtain a high dynamic range image by using multi-exposure fusion. Unlike previous methods that have many restrictions such as requiring camera response function, sensor noise model, and a stream of preview images with different exposures (not accessible in some scenarios e.g. mobile applications), we propose a novel deep neural network to automatically select exposure bracketing, named EBSNet, which is sufficiently flexible without having the above restrictions. EBSNet is formulated as a reinforced agent that is trained by maximizing rewards provided by a multi-exposure fusion network (MEFNet). By utilizing the illumination and semantic information extracted from just a single auto-exposure preview image, EBSNet enables to select an optimal exposure bracketing for multi-exposure fusion. EBSNet and MEFNet can be jointly trained to produce favorable results against recent state-of-the-art approaches. To facilitate future research, we provide a new benchmark dataset for multi-exposure selection and fusion.

Time-of-Flight (ToF) cameras require active illumination to obtain depth information thus the power of illumination directly affects the performance of ToF cameras. Traditional ToF imaging algorithms are very sensitive to illumination and the depth accuracy degenerates rapidly with the power of it. Therefore, the design of a power efficient ToF camera always creates a painful dilemma for the illumination and the performance trade-off. In this paper, we show that despite the weak signals in many areas under extreme short exposure setting, these signals as a whole can be well utilized through a learning process which directly translates the weak and noisy ToF camera raw to depth map. This creates an opportunity to tackle the aforementioned dilemma and make a very power efficient ToF camera possible. To enable the learning, we collect a comprehensive dataset under a variety of scenes and photographic conditions by a specialized ToF camera. Experiments show that our method is able to robustly process ToF camera raw with the exposure time of one order of magnitude shorter than that used in conventional ToF cameras. In addition to evaluating our approach both quantitatively and qualitatively, we also discuss its implication to designing the next generation power efficient ToF cameras.

Synthesizing a novel view from different viewpoints has been an essential problem in 3D vision. Among a variety of view synthesis tasks, single image based view synthesis is particularly challenging. Recent works address this problem by a fixed number of image planes of discrete disparities, which tend to generate structurally inconsistent results on wide-baseline, scene-complicated datasets such as KITTI. In this paper, we propose the Self-Guided Elastic Displacement Network (SG-EDN), which explicitly models the geometric transformation by a novel non-discrete scene representation called layered displacement maps (LDM). To generate realistic views, we exploit the positional characteristics of the displacement maps and design a multi-scale structural pyramid for self-guided filtering on the displacement maps. To optimize efficiency and scene-adaptivity, we allow the effective range of each displacement map to be `elastic', with fully learnable parameters. Experimental results confirm that our framework outperforms existing methods in both quantitative and qualitative tests.

This paper addresses stereoscopic view synthesis from a single image. Various recent works solve this task by reorganizing pixels from the input view to reconstruct the target one in a stereo setup. However, purely depending on such photometric-based reconstruction process, the network may produce structurally inconsistent results. Regarding this issue, this work proposes Multi-Scale Adversarial Correlation Matching (MS-ACM), a novel learning framework for structure-aware view synthesis. The proposed framework does not assume any costly supervision signal of scene structures such as depth. Instead, it models structures as self-correlation coefficients extracted from multi-scale feature maps in transformed spaces. In training, the feature space attempts to push the correlation distances between the synthesized and target images far apart, thus amplifying inconsistent structures. At the same time, the view synthesis network minimizes such correlation distances by fixing mistakes it makes. With such adversarial training, structural errors of different scales and levels are iteratively discovered and reduced, preserving both global layouts and fine-grained details. Extensive experiments on the KITTI benchmark show that MS-ACM improves both visual quality and the metrics over existing methods when plugged into recent view synthesis architectures.

Joint filtering mainly uses an additional guidance image as a prior and transfers its structures to the target image in the filtering process. Different from existing algorithms that rely on locally linear models or hand-designed objective functions to extract the structural information from the guidance image, we propose a new joint filter based on a spatially variant linear representation model (SVLRM), where the target image is linearly represented by the guidance image. However, the SVLRM leads to a highly ill-posed problem. To estimate the linear representation coefficients, we develop an effective algorithm based on a deep convolutional neural network (CNN). The proposed deep CNN (constrained by the SVLRM) is able to estimate the spatially variant linear representation coefficients which are able to model the structural information of both the guidance and input images. We show that the proposed algorithm can be effectively applied to a variety of applications, including depth/RGB image upsampling and restoration, flash/no-flash image deblurring, natural image denoising, scale-aware filtering, etc. Extensive experimental results demonstrate that the proposed algorithm performs favorably against state-of-the-art methods that have been specially designed for each task.

Nowadays stereo cameras are more commonly adopted in emerging devices such as dual-lens smartphones and unmanned aerial vehicles. However, they also suffer from blurry images in dynamic scenes which leads to visual discomfort and hampers further image processing. Previous works have succeeded in monocular deblurring, yet there are few studies on deblurring for stereoscopic images. By exploiting the two-view nature of stereo images, we propose a novel stereo image deblurring network with Depth Awareness and View Aggregation, named DAVANet. In our proposed network, 3D scene cues from the depth and varying information from two views are incorporated, which help to remove complex spatially-varying blur in dynamic scenes. Specifically, with our proposed fusion network, we integrate the bidirectional disparities estimation and deblurring into a unified framework. Moreover, we present a large-scale multi-scene dataset for stereo deblurring, containing 20,637 blurry-sharp stereo image pairs from 135 diverse sequences and their corresponding bidirectional disparities. The experimental results on our dataset demonstrate that DAVANet outperforms state-of-the-art methods in terms of accuracy, speed, and model size.

Recently, consistency-based methods have achieved state-of-the-art results in semi-supervised learning (SSL). These methods always involve two roles, an explicit or implicit teacher model and a student model, and penalize predictions under different perturbations by a consistency constraint. However, the weights of these two roles are tightly coupled since the teacher is essentially an exponential moving average (EMA) of the student. In this work, we show that the coupled EMA teacher causes a performance bottleneck. To address this problem, we introduce Dual Student, which replaces the teacher with another student. We also define a novel concept, stable sample, following which a stabilization constraint is designed for our structure to be trainable. Further, we discuss two variants of our method, which produce even higher performance. Extensive experiments show that our method improves the classification performance significantly on several main SSL benchmarks. Specifically, it reduces the error rate of the 13-layer CNN from 16.84% to 12.39% on CIFAR-10 with 1k labels and from 34.10% to 31.56% on CIFAR-100 with 10k labels. In addition, our method also achieves a clear improvement in domain adaptation.

Image dehazing is a well-known ill-posed problem, which usually requires some image priors to make the problem well-posed. We propose an effective iteration algorithm with deep CNNs to learn haze-relevant priors for image dehazing. We formulate the image dehazing problem as the minimization of a variational model with favorable data fidelity terms and prior terms to regularize the model. We solve the variational model based on the classical gradient descent method with built-in deep CNNs so that iteration-wise image priors for the atmospheric light, transmission map and clear image can be well estimated. Our method combines the properties of both the physical formation of image dehazing as well as deep learning approaches. We show that it is able to generate clear images as well as accurate atmospheric light and transmission maps. Extensive experimental results demonstrate that the proposed algorithm performs favorably against state-of-the-art methods in both benchmark datasets and real-world images.

Video deblurring is a challenging task due to the spatially variant blur caused by camera shake, object motions, and depth variations, etc. Existing methods usually estimate optical flow in the blurry video to align consecutive frames or approximate blur kernels. However, they tend to generate artifacts or cannot effectively remove blur when the estimated optical flow is not accurate. To overcome the limitation of separate optical flow estimation, we propose a Spatio-Temporal Filter Adaptive Network (STFAN) for the alignment and deblurring in a unified framework. The proposed STFAN takes both blurry and restored images of the previous frame as well as blurry image of the current frame as input, and dynamically generates the spatially adaptive filters for the alignment and deblurring. We then propose the new Filter Adaptive Convolutional (FAC) layer to align the deblurred features of the previous frame with the current frame and remove the spatially variant blur from the features of the current frame. Finally, we develop a reconstruction network which takes the fusion of two transformed features to restore the clear frames. Both quantitative and qualitative evaluation results on the benchmark datasets and real-world videos demonstrate that the proposed algorithm performs favorably against state-of-the-art methods in terms of accuracy, speed as well as model size.

In the past a few years, we witnessed rapid advancement in face super-resolution from very low resolution(VLR) images. However, most of the previous studies focus on solving such problem without explicitly considering the impact of severe real-life image degradation (e.g. blur and noise). We can show that robustly recover details from VLR images is a task beyond the ability of current state-of-the-art method. In this paper, we borrow ideas from "facial composite" and propose an alternative approach to tackle this problem. We endow the degraded VLR images with additional cues by integrating existing face components from multiple reference images into a novel learning pipeline with both low level and high level semantic loss function as well as a specialized adversarial based training scheme. We show that our method is able to effectively and robustly restore relevant facial details from 16x16 images with extreme degradation. We also tested our approach against real-life images and our method performs favorably against previous methods.

With the developments of dual-lens camera modules, depth information representing the third dimension of the captured scenes becomes available for smartphones. It is estimated by stereo matching algorithms, taking as input the two views captured by dual-lens cameras at slightly different viewpoints. Depth-of-field rendering (also be referred to as synthetic defocus or bokeh) is one of the trending depth-based applications. However, to achieve fast depth estimation on smartphones, the stereo pairs need to be rectified in the first place. In this paper, we propose a cost-effective solution to perform stereo rectification for dual-lens cameras called direct self-rectification, short for DSR. It removes the need of individual offline calibration for every pair of dual-lens cameras. In addition, the proposed solution is robust to the slight movements, {\it e.g.}, due to collisions, of the dual-lens cameras after fabrication. Different with existing self-rectification approaches, our approach computes the homography in a novel way with zero geometric distortions introduced to the master image. It is achieved by directly minimizing the vertical displacements of corresponding points between the original master image and the transformed slave image. Our method is evaluated on both realistic and synthetic stereo image pairs, and produces superior results compared to the calibrated rectification or other self-rectification approaches.

Artistic style transfer can be thought as a process to generate different versions of abstraction of the original image. However, most of the artistic style transfer operators are not optimized for human faces thus mainly suffers from two undesirable features when applying them to selfies. First, the edges of human faces may unpleasantly deviate from the ones in the original image. Second, the skin color is far from faithful to the original one which is usually problematic in producing quality selfies. In this paper, we take a different approach and formulate this abstraction process as a gradient domain learning problem. We aim to learn a type of abstraction which not only achieves the specified artistic style but also circumvents the two aforementioned drawbacks thus highly applicable to selfie photography. We also show that our method can be directly generalized to videos with high inter-frame consistency. Our method is also robust to non-selfie images, and the generalization to various kinds of real-life scenes is discussed. We will make our code publicly available.

Previous monocular depth estimation methods take a single view and directly regress the expected results. Though recent advances are made by applying geometrically inspired loss functions during training, the inference procedure does not explicitly impose any geometrical constraint. Therefore these models purely rely on the quality of data and the effectiveness of learning to generalize. This either leads to suboptimal results or the demand of huge amount of expensive ground truth labelled data to generate reasonable results. In this paper, we show for the first time that the monocular depth estimation problem can be reformulated as two sub-problems, a view synthesis procedure followed by stereo matching, with two intriguing properties, namely i) geometrical constraints can be explicitly imposed during inference; ii) demand on labelled depth data can be greatly alleviated. We show that the whole pipeline can still be trained in an end-to-end fashion and this new formulation plays a critical role in advancing the performance. The resulting model outperforms all the previous monocular depth estimation methods as well as the stereo block matching method in the challenging KITTI dataset by only using a small number of real training data. The model also generalizes well to other monocular depth estimation benchmarks. We also discuss the implications and the advantages of solving monocular depth estimation using stereo methods.

We observed that recent state-of-the-art results on single image human pose estimation were achieved by multistage Convolution Neural Networks (CNN). Notwithstanding the superior performance on static images, the application of these models on videos is not only computationally intensive, it also suffers from performance degeneration and flicking. Such suboptimal results are mainly attributed to the inability of imposing sequential geometric consistency, handling severe image quality degradation (e.g. motion blur and occlusion) as well as the inability of capturing the temporal correlation among video frames. In this paper, we proposed a novel recurrent network to tackle these problems. We showed that if we were to impose the weight sharing scheme to the multi-stage CNN, it could be re-written as a Recurrent Neural Network (RNN). This property decouples the relationship among multiple network stages and results in significantly faster speed in invoking the network for videos. It also enables the adoption of Long Short-Term Memory (LSTM) units between video frames. We found such memory augmented RNN is very effective in imposing geometric consistency among frames. It also well handles input quality degradation in videos while successfully stabilizes the sequential outputs. The experiments showed that our approach significantly outperformed current state-of-the-art methods on two large-scale video pose estimation benchmarks. We also explored the memory cells inside the LSTM and provided insights on why such mechanism would benefit the prediction for video-based pose estimations.1

In this paper, we propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining and dehazing. These problems usually involve the estimation of two components of the target signals: structures and details. Motivated by this, our proposed DualCNN consists of two parallel branches, which respectively recovers the structures and details in an end-to-end manner. The recovered structures and details can generate the target signals according to the formation model for each particular application. The DualCNN is a flexible framework for low-level vision tasks and can be easily incorporated into existing CNNs. Experimental results show that the DualCNN can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods.

Despite the recent success of stereo matching with convolutional neural networks (CNNs), it remains arduous to generalize a pre-trained deep stereo model to a novel domain. A major difficulty is to collect accurate ground-truth disparities for stereo pairs in the target domain. In this work, we propose a self-adaptation approach for CNN training, utilizing both synthetic training data (with ground-truth disparities) and stereo pairs in the new domain (without ground-truths). Our method is driven by two empirical observations. By feeding real stereo pairs of different domains to stereo models pre-trained with synthetic data, we see that: i) a pre-trained model does not generalize well to the new domain, producing artifacts at boundaries and ill-posed regions; however, ii) feeding an up-sampled stereo pair leads to a disparity map with extra details. To avoid i) while exploiting ii), we formulate an iterative optimization problem with graph Laplacian regularization. At each iteration, the CNN adapts itself better to the new domain: we let the CNN learn its own higher-resolution output; at the meanwhile, a graph Laplacian regularization is imposed to discriminatively keep the desired edges while smoothing out the artifacts. We demonstrate the effectiveness of our method in two domains: daily scenes collected by smart-phone cameras, and street views captured in a driving car.

Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DCNNs). Despite their success on large-scale datasets collected in the constrained lab environment, it is difficult to obtain the 3D pose annotations for in-the-wild images. Therefore, 3D human pose estimation in the wild is still a challenge. In this paper, we propose an adversarial learning framework, which distills the 3D human pose structures learned from the fully annotated dataset to in-the-wild images with only 2D pose annotations. Instead of defining hard-coded rules to constrain the pose estimation results, we design a novel multi-source discriminator to distinguish the predicted 3D poses from the ground-truth, which helps to enforce the pose estimator to generate anthropometrically valid poses even with images in the wild. We also observe that a carefully designed information source for the discriminator is essential to boost the performance. Thus, we design a geometric descriptor, which computes the pairwise relative locations and distances between body joints, as a new information source for the discriminator. The efficacy of our adversarial learning framework with the new geometric descriptor has been demonstrated through extensive experiments on widely used public benchmarks. Our approach significantly improves the performance compared with previous state-of-the-art approaches.

Due to the spatially variant blur caused by camera shake and object motions under different scene depths, deblurring images captured from dynamic scenes is challenging. Although recent works based on deep neural networks have shown great progress on this problem, their models are usually large and computationally expensive. In this paper, we propose a novel spatially variant neural network to address the problem. The proposed network is composed of three deep convolutional neural networks (CNNs) and a recurrent neural network (RNN). RNN is used as a deconvolution operator performed on feature maps extracted from the input image by one of the CNNs. Another CNN is used to learn the weights for the RNN at every location. As a result, the RNN is spatially variant and could implicitly model the deblurring process with spatially variant kernels. The third CNN is used to reconstruct the final deblurred feature maps into restored image. The whole network is end-to-end trainable. Our analysis shows that the proposed network has a large receptive field even with a small model size. Quantitative and qualitative evaluations on public datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of accuracy, speed, and model size.

Social relationships (e.g., friends, couple etc.) form the basis of the social network in our daily life. Automatically interpreting such relationships bears a great potential for the intelligent systems to understand human behavior in depth and to better interact with people at a social level. Human beings interpret the social relationships within a group not only based on the people alone, and the interplay between such social relationships and the contextual information around the people also plays a significant role. However, these additional cues are largely overlooked by the previous studies. We found that the interplay between these two factors can be effectively modeled by a novel structured knowledge graph with proper message propagation and attention. And this structured knowledge can be efficiently integrated into the deep neural network architecture to promote social relationship understanding by an end-to-end trainable Graph Reasoning Model (GRM), in which a propagation mechanism is learned to propagate node message through the graph to explore the interaction between persons of interest and the contextual objects. Meanwhile, a graph attentional mechanism is introduced to explicitly reason about the discriminative objects to promote recognition. Extensive experiments on the public benchmarks demonstrate the superiority of our method over the existing leading competitors.

Most of the recent successful methods in accurate object detection and localization used some variants of R-CNN style two stage Convolutional Neural Networks (CNN) where plausible regions were proposed in the first stage then followed by a second stage for decision refinement. Despite the simplicity of training and the efficiency in deployment, the single stage detection methods have not been as competitive when evaluated in benchmarks consider mAP for high IoU thresholds. In this paper, we proposed a novel single stage end-to-end trainable object detection network to overcome this limitation. We achieved this by introducing Recurrent Rolling Convolution (RRC) architecture over multi-scale feature maps to construct object classifiers and bounding box regressors which are deep in context. We evaluated our method in the challenging KITTI dataset which measures methods under IoU threshold of 0.7. We showed that with RRC, a single reduced VGG-16 based model already significantly outperformed all the previously published results. At the time this paper was written our models ranked the first in KITTI car detection (the hard level), the first in cyclist detection and the second in pedestrian detection. These results were not reached by the previous single stage methods. The code is publicly available.

Speaker identification refers to the task of localizing the face of a person who has the same identity as the ongoing voice in a video. This task not only requires collective perception over both visual and auditory signals, the robustness to handle severe quality degradations and unconstrained content variations are also indispensable. In this paper, we describe a novel multimodal Long Short-Term Memory (LSTM) architecture which seamlessly unifies both visual and auditory modalities from the beginning of each sequence input. The key idea is to extend the conventional LSTM by not only sharing weights across time steps, but also sharing weights across modalities. We show that modeling the temporal dependency across face and voice can significantly improve the robustness to content quality degradations and variations. We also found that our multimodal LSTM is robustness to distractors, namely the non-speaking identities. We applied our multimodal LSTM to The Big Bang Theory dataset and showed that our system outperforms the state-of-the-art systems in speaker identification with lower false alarm rate and higher recognition accuracy.

We recently have witnessed many ground-breaking results in machine learning and computer vision, generated by using deep convolutional neural networks (CNN). While the success mainly stems from the large volume of training data and the deep network architectures, the vector processing hardware (e.g. GPU) undisputedly plays a vital role in modern CNN implementations to support massive computation. Though much attention was paid in the extent literature to understand the algorithmic side of deep CNN, little research was dedicated to the vectorization for scaling up CNNs. In this paper, we studied the vectorization process of key building blocks in deep CNNs, in order to better understand and facilitate parallel implementation. Key steps in training and testing deep CNNs are abstracted as matrix and vector operators, upon which parallelism can be easily achieved. We developed and compared six implementations with various degrees of vectorization with which we illustrated the impact of vectorization on the speed of model training and testing. Besides, a unified CNN framework for both high-level and low-level vision tasks is provided, along with a vectorized Matlab implementation with state-of-the-art speed performance.

There are many edge-aware filters varying in their construction forms and filtering properties. It seems impossible to uniformly represent and accelerate them in a single framework. We made the attempt to learn a big and important family of edge-aware operators from data. Our method is based on a deep convolutional neural network with a gradient domain training procedure, which gives rise to a powerful tool to approximate various filters without knowing the original models and implementation details. The only difference among these operators in our system becomes merely the learned parameters. Our system enables fast approximation for complex edge-aware filters and achieves up to 200x acceleration, regardless of their originally very different implementation. Fast speed can also be achieved when creating new effects using spatially varying filter or filter combination, bearing out the effectiveness of our deep edge-aware filters.

Automatic speaker naming is the problem of localizing as well as identifying each speaking character in a TV/movie/live show video. This is a challenging problem mainly attributes to its multimodal nature, namely face cue alone is insufficient to achieve good performance. Previous multimodal approaches to this problem usually process the data of different modalities individually and merge them using handcrafted heuristics. Such approaches work well for simple scenes, but fail to achieve high performance for speakers with large appearance variations. In this paper, we propose a novel convolutional neural networks (CNN) based learning framework to automatically learn the fusion function of both face and audio cues. We show that without using face tracking, facial landmark localization or subtitle/transcript, our system with robust multimodal feature extraction is able to achieve state-of-the-art speaker naming performance evaluated on two diverse TV series. The dataset and implementation of our algorithm are publicly available online.

Deep learning has recently been introduced to the field of low-level computer vision and image processing. Promising results have been obtained in a number of tasks including super-resolution, inpainting, deconvolution, filtering, etc. However, previously adopted neural network approaches such as convolutional neural networks and sparse auto-encoders are inherently with translation invariant operators. We found this property prevents the deep learning approaches from outperforming the state-of-the-art if the task itself requires translation variant interpolation (TVI). In this paper, we draw on Shepard interpolation and design Shepard Convolutional Neural Networks (ShCNN) which efficiently realizes end-to-end trainable TVI operators in the network. We show that by adding only a few feature maps in the new Shepard layers, the network is able to achieve stronger results than a much deeper architecture. Superior performance on both image inpainting and super-resolution is obtained where our system outperforms previous ones while keeping the running time competitive.

This paper proposes a model to calculate the average speed of transmission of intervehicle communication (IVC) messages in a general traffic stream on highways in the early stage of deploying distributed traffic information systems (DTIS). The model helps explain the relationship between average IVC message speed and traffic parameters such as equipped vehicle density, traffic flow speed, and traffic direction. Simulation results are used to verify the correctness of the model. This model needs a much shorter calculation time than a simulation. Moreover, the theoretical analysis helps provide more insightful explanations of the phenomenon for IVC performance analysis. The results of this paper would help people better understand the design criteria for DTIS.

With the proliferation of its applications in various industries, sentiment analysis by using publicly available web data has become an active research area in text classification during these years. It is argued by researchers that semi-supervised learning is an effective approach to this problem since it is capable to mitigate the manual labeling effort which is usually expensive and time-consuming. However, there was a long-term debate on the effectiveness of unlabeled data in text classification. This was partially caused by the fact that many assumptions in theoretic analysis often do not hold in practice. We argue that this problem may be further understood by adding an additional dimension in the experiment. This allows us to address this problem in the perspective of bias and variance in a broader view. We show that the well-known performance degradation issue caused by unlabeled data can be reproduced as a subset of the whole scenario. We argue that if the bias-variance trade-off is to be better balanced by a more effective feature selection method unlabeled data is very likely to boost the classification performance. We then propose a feature selection framework in which labeled and unlabeled training samples are both considered. We discuss its potential in achieving such a balance. Besides, the application in financial sentiment analysis is chosen because it not only exemplifies an important application, the data possesses better illustrative power as well. The implications of this study in text classification and financial sentiment analysis are both discussed.