Given a single input rainy image, our goal is to visually remove rain streaks and the veiling effect caused by scattering and transmission of rain streaks and rain droplets. We are particularly concerned with heavy rain, where rain streaks of various sizes and directions can overlap each other and the veiling effect reduces contrast severely. To achieve our goal, we introduce a scale-aware multi-stage convolutional neural network. Our main idea here is that different sizes of rain-streaks visually degrade the scene in different ways. Large nearby streaks obstruct larger regions and are likely to reflect specular highlights more prominently than smaller distant streaks. These different effects of different streaks have their own characteristics in their image features, and thus need to be treated differently. To realize this, we create parallel sub-networks that are trained and made aware of these different scales of rain streaks. To our knowledge, this idea of parallel sub-networks that treats the same class of objects according to their unique sub-classes is novel, particularly in the context of rain removal. To verify our idea, we conducted experiments on both synthetic and real images, and found that our method is effective and outperforms the state-of-the-art methods.
Rain streaks can severely degrade the visibility, which causes many current computer vision algorithms fail to work. So it is necessary to remove the rain from images. We propose a novel deep network architecture based on deep convolutional and recurrent neural networks for single image deraining. As contextual information is very important for rain removal, we first adopt the dilated convolutional neural network to acquire large receptive field. To better fit the rain removal task, we also modify the network. In heavy rain, rain streaks have various directions and shapes, which can be regarde…
Tianjin University（天津大学）；Harbin Institute of Technology（哈尔滨工业大学）；Xi’an Jiaotong University（西安交通大学）
Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new deraining networks. To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions. Specifically, by repeatedly unfolding a shallow ResNet, progressive ResNet (PRN) is proposed to take advantage of recursive computation. A recurrent layer is further introduced …
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Lingnan University（岭南大学）；Ryerson University（瑞尔森大学）；Hong Kong Polytechnic University（香港理工大学）
We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively …
Deep learning algorithms have recently achieved promising deraining performances on both the natural and synthetic rainy datasets. As an essential low-level pre-processing stage, a deraining network should clear the rain streaks and preserve the fine semantic details. However, most existing methods only consider low-level image restoration. That limits their performances at high-level tasks requiring precise semantic information. To address this issue, in this paper, we present a segmentation-aware progressive network (SAPNet) based upon contrastive learning for single image deraining. We star…
Wuhan University of Science and Technology（武汉科技大学）
It is challenging to remove rain-steaks from a single rainy image because the rain steaks are spatially varying in the rainy image. This problem is studied in this paper by combining conventional image processing techniques and deep learning based techniques. An improved weighted guided image filter (iWGIF) is proposed to extract high frequency information from a rainy image. The high frequency information mainly includes rain steaks and noise, and it can guide the rain steaks aware deep convolutional neural network (RSADCNN) to pay more attention to rain steaks. The efficiency and explain-abi…
Nanyang Technological University（南洋理工大学）；Kyushu University（九州大学）；University of Alberta（阿尔伯塔大学）；Alibaba Group（阿里巴巴集团）；Tianjin University（天津大学）；University of South Carolina（南卡罗来纳大学）
Deraining is a significant and fundamental computer vision task, aiming to remove the rain streaks and accumulations in an image or video captured under a rainy day. Existing deraining methods usually make heuristic assumptions of the rain model, which compels them to employ complex optimization or iterative refinement for high recovery quality. This, however, leads to time-consuming methods and affects the effectiveness for addressing rain patterns deviated from from the assumptions. In this paper, we propose a simple yet efficient deraining method by formulating deraining as a predictive fil…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Inception Institute of Artificial Intelligence（启元人工智能研究院）；Meituan Group（美团集团）；Australian National University（澳大利亚国立大学）；Tencent（腾讯）；Beijing Institute of Technology（北京理工大学）
Rain is a common natural phenomenon. Taking images in the rain however often results in degraded quality of images, thus compromises the performance of many computer vision systems. Most existing de-rain algorithms use only one single input image and aim to recover a clean image. Few work has exploited stereo images. Moreover, even for single image based monocular deraining, many current methods fail to complete the task satisfactorily because they mostly rely on per pixel loss functions and ignore semantic information. In this paper, we present a Paired Rain Removal Network (PRRNet), which ex…
City University of Hong Kong（香港城市大学）；Yale-NUS College（耶鲁-新加坡国立大学学院）；National University of Singapore（新加坡国立大学）；Jiangxi University of Finance and Economics（江西财经大学）；Peking University（北京大学）
The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation. The early single-image deraining methods employ a cost function, where various priors are developed to represent the properties of rain and background layers. Since 2017, single-image deraining methods step into a deep-learning era, and exploit various types of networks, i.e. convolutional neural networks, recurrent neural networks, generative adversarial networks, etc., demonstrating impressive performance. Given the current rapid development, in this pa…
University of Science and Technology of China（中国科学技术大学）；KDDI Research, Inc.（KDDI研究所）
Image deraining is an important image processing task as rain streaks not only severely degrade the visual quality of images but also significantly affect the performance of high-level vision tasks. Traditional methods progressively remove rain streaks via different recurrent neural networks. However, these methods fail to yield plausible rain-free images in an efficient manner. In this paper, we propose a residual squeeze-and-excitation network called RSEN for fast image deraining as well as superior deraining performance compared with state-of-the-art approaches. Specifically, RSEN adopts a …
Single image deraining is typically addressed as residual learning to predict the rain layer from an input rainy image. For this purpose, an encoder-decoder network draws wide attention, where the encoder is required to encode a high-quality rain embedding which determines the performance of the subsequent decoding stage to reconstruct the rain layer. However, most of existing studies ignore the significance of rain embedding quality, thus leading to limited performance with over/under-deraining. In this paper, with our observation of the high rain layer reconstruction performance by an rain-t…
We develop a new physical model for the rain effect and show that the well-known atmosphere scattering model (ASM) for the haze effect naturally emerges as its homogeneous continuous limit. Via depth-aware fusion of multi-layer rain streaks according to the camera imaging mechanism, the new model can better capture the sophisticated non-deterministic degradation patterns commonly seen in real rainy images. We also propose a Densely Scale-Connected Attentive Network (DSCAN) that is suitable for both deraining and dehazing tasks. Our design alleviates the bottleneck issue existent in conventiona…
Wuhan University（武汉大学）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）；King’s College London（伦敦国王学院）；Harbin Institute of Technology（哈尔滨工业大学）
Rain streaks in the air appear in various blurring degrees and resolutions due to different distances from their positions to the camera. Similar rain patterns are visible in a rain image as well as its multi-scale (or multi-resolution) versions, which makes it possible to exploit such complementary information for rain streak representation. In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi-scale progressive fusion network (MSPFN) for single image…
Rain often poses inevitable threats to deep neural network (DNN) based perception systems, and a comprehensive investigation of the potential risks of the rain to DNNs is of great importance. However, it is rather difficult to collect or synthesize rainy images that can represent all rain situations that would possibly occur in the real world. To this end, in this paper, we start from a new perspective and propose to combine two totally different studies, i.e., rainy image synthesis and adversarial attack. We first present an adversarial rain attack, with which we could simulate various rain s…
Vietnam National Space Center（越南国家航天中心）；Vietnam Academy of Science and Technology（越南科学技术研究院）；Gachon University（嘉泉大学）
Image deraining is a new challenging problem in applications of autonomous vehicles. In a bad weather condition of heavy rainfall, raindrops, mainly hitting the vehicle's windshield, can significantly reduce observation ability even though the windshield wipers might be able to remove part of it. Moreover, rain flows spreading over the windshield can yield the physical effect of refraction, which seriously impede the sightline or undermine the machine learning system equipped in the vehicle. In this paper, we propose a new multi-stage multi-task recurrent generative adversarial network (M2GAN)…
We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations in the world scene and latent feature locations. Object detection, object segmentation, and 3D reconstruction is then carried out directly using the constructed 3D feature memory, as opposed to any of the input 2D images. The proposed models are equipped with differentiable egomotion-aware feature warping and (learned) depth-aware unprojection operations to achieve geometrical…
In this paper, we address the challenging problem of efficient temporal activity detection in untrimmed long videos. While most recent work has focused and advanced the detection accuracy, the inference time can take seconds to minutes in processing each single video, which is too slow to be useful in real-world settings. This motivates the proposed budget-aware framework, which learns to perform activity detection by intelligently selecting a small subset of frames according to a specified time budget. We formulate this problem as a Markov decision process, and adopt a recurrent network to mo…
Recent deep learning based salient object detection methods which utilize both saliency and boundary features have achieved remarkable performance. However, most of them ignore the complementarity between saliency features and boundary features, thus get worse predictions in scenes with low contrast between foreground and background. To address this issue, we propose a novel Recurrent Two-Stream Guided Refinement Network (RTGRNet) that consists of iterating Two-Stream Guided Refinement Modules (TGRMs). TGRM consists of a Guide Block and two feature streams: saliency and boundary, the Guide Blo…
Sun Yat-sen University（中山大学）；The University of Sydney（悉尼大学）
Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera's perspective that causes huge appearance variations in people's scales and rotations. Conventional methods address such challenges by resorting to fixed multi-scale architectures that are often unable to cover the largely varied scales while ignoring the rotation variations. In this paper, we propose a unified neural network framework, named Deep Recurrent Spatial-Aware Network, which adaptively addresses the two is…
We integrate two powerful ideas, geometry and deep visual representation learning, into recurrent network architectures for mobile visual scene understanding. The proposed networks learn to "lift" and integrate 2D visual features over time into latent 3D feature maps of the scene. They are equipped with differentiable geometric operations, such as projection, unprojection, egomotion estimation and stabilization, in order to compute a geometrically-consistent mapping between the world scene and their 3D latent feature state. We train the proposed architectures to predict novel camera views give…
Recurrent networks have been successful in analyzing temporal data and have been widely used for video analysis. However, for video face recognition, where the base CNNs trained on large-scale data already provide discriminative features, using Long Short-Term Memory (LSTM), a popular recurrent network, for feature learning could lead to overfitting and degrade the performance instead. We propose a Recurrent Embedding Aggregation Network (REAN) for set to set face recognition. Compared with LSTM, REAN is robust against overfitting because it only learns how to aggregate the pre-trained embeddi…
Anatomically Conditioned Recurrent Refinement for Topology-Aware Circle of Willis Segmentation
Faculty of Electrical Engineering, Computer Science and Information Technology, Osijek, Croatia（奥西耶克大学电气工程、计算机科学与信息技术学院）；Clinical Medical Center Osijek, Osijek, Croatia（奥西耶克临床医学中心）；Ghent University, Dept. of Telecommunications and Information Processing, imec-TELIN-IPI, Ghent, Belgium（根特大学电信与信息处理系，imec-TELIN-IPI）；Ghent University, Dept. of Telecommunications and Information Processing, TELIN-GAIM, Ghent, Belgium（根特大学电信与信息处理系，TELIN-GAIM）
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
The use of Recurrent Neural Networks for video captioning has recently gained a lot of attention, since they can be used both to encode the input video and to generate the corresponding description. In this paper, we present a recurrent video encoding scheme which can discover and leverage the hierarchical structure of the video. Unlike the classical encoder-decoder approach, in which a video is encoded continuously by a recurrent layer, we propose a novel LSTM cell, which can identify discontinuity points between frames or segments and modify the temporal connections of the encoding layer acc…
Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video simultaneously - significantly enhances the performance of such systems, especially in noisy environments. This work presents the design of such an audio-visual system for Automated Speech Recognition, taking memory and computation requirements into account. First, a Long-Short-Term-Memory neural network for acoustic speech recognition is designed. Second, Convolutiona…
Objects may appear at arbitrary scales in perspective images of a scene, posing a challenge for recognition systems that process images at a fixed resolution. We propose a depth-aware gating module that adaptively selects the pooling field size in a convolutional network architecture according to the object scale (inversely proportional to the depth) so that small details are preserved for distant objects while larger receptive fields are used for those nearby. The depth gating signal is provided by stereo disparity or estimated directly from monocular input. We integrate this depth-aware gati…
Institute for Intelligent Systems Research and Innovation, Deakin University（迪肯大学智能系统研究与革新研究所）；School of Medicine, Deakin University（迪肯大学医学院）
In this paper, we proposed using a hybrid method that utilises deep convolutional and recurrent neural networks for accurate delineation of skin lesion of images supplied with ISBI 2017 lesion segmentation challenge. The proposed method was trained using 1800 images and tested on 150 images from ISBI 2017 challenge.
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
Stereo reconstruction models trained on small images do not generalize well to high-resolution data. Training a model on high-resolution image size faces difficulties of data availability and is often infeasible due to limited computing resources. In this work, we present the Occlusion-aware Recurrent binocular Stereo matching (ORStereo), which deals with these issues by only training on available low disparity range stereo images. ORStereo generalizes to unseen high-resolution images with large disparity ranges by formulating the task as residual updates and refinements of an initial predicti…
NVIDIA（英伟达）；ETH Zurich（苏黎世联邦理工学院）；The Swiss AI Lab IDSIA（瑞士人工智能实验室IDSIA）；NNAISENSE
Video prediction models based on convolutional networks, recurrent networks, and their combinations often result in blurry predictions. We identify an important contributing factor for imprecise predictions that has not been studied adequately in the literature: blind spots, i.e., lack of access to all relevant past information for accurately predicting the future. To address this issue, we introduce a fully context-aware architecture that captures the entire available past context for each pixel using Parallel Multi-Dimensional LSTM units and aggregates it using blending units. Our model outp…
National Tsing Hua University（国立清华大学）；National Chengchi University（国立政治大学）；Qualcomm Technologies, Inc.（高通技术公司）；National Yang Ming Chiao Tung University（国立阳明交通大学）
Image motion blur results from a combination of object motions and camera shakes, and such blurring effect is generally directional and non-uniform. Previous research attempted to solve non-uniform blurs using self-recurrent multiscale, multi-patch, or multi-temporal architectures with self-attention to obtain decent results. However, using self-recurrent frameworks typically lead to a longer inference time, while inter-pixel or inter-channel self-attention may cause excessive memory usage. This paper proposes a Blur-aware Attention Network (BANet), that accomplishes accurate and efficient deb…
Sun Yat-Sen University（中山大学）；University of Edinburgh（爱丁堡大学）；Cardiovascular Research Centre, Royal Brompton Hospital（皇家布朗普顿医院心血管研究中心）；National Heart & Lung Institute, Imperial College London（帝国理工学院国家心肺研究所）
The performance of traditional compressive sensing-based MRI (CS-MRI) reconstruction is affected by its slow iterative procedure and noise-induced artefacts. Although many deep learning-based CS-MRI methods have been proposed to mitigate the problems of traditional methods, they have not been able to achieve more robust results at higher acceleration factors. Most of the deep learning-based CS-MRI methods still can not fully mine the information from the k-space, which leads to unsatisfactory results in the MRI reconstruction. In this study, we propose a new deep learning-based CS-MRI reconstr…
Text-to-image synthesis aims to generate natural images conditioned on text descriptions. The main difficulty of this task lies in effectively fusing text information into the image synthesis process. Existing methods usually adaptively fuse suitable text information into the synthesis process with multiple isolated fusion blocks (e.g., Conditional Batch Normalization and Instance Normalization). However, isolated fusion blocks not only conflict with each other but also increase the difficulty of training (see first page of the supplementary). To address these issues, we propose a Recurrent Af…
College of Information Science & Technology, Beijing University of Chemical Technology（北京化工大学信息科学与技术学院）；National Research Center for High-Performance Computing Engineering Technology, Sugon Information Industry Co., Ltd（曙光信息产业股份有限公司高性能计算工程技术国家研究中心）；Sichuan Provincial Key Laboratory of Information Coding and Transmission, Southwest Jiaotong University（西南交通大学信息编码与传输四川省重点实验室）；Institute of Electronics, Chinese Academy of Sciences（中国科学院电子学研究所）
The outstanding pattern recognition performance of deep learning brings new vitality to the synthetic aperture radar (SAR) automatic target recognition (ATR). However, there is a limitation in current deep learning based ATR solution that each learning process only handle one SAR image, namely learning the static scattering information, while missing the space-varying information. It is obvious that multi-aspect joint recognition introduced space-varying scattering information should improve the classification accuracy and robustness. In this paper, a novel multi-aspect-aware method is propose…
Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）
Image-guided adaptive lung radiotherapy requires accurate tumor and organs segmentation from during treatment cone-beam CT (CBCT) images. Thoracic CBCTs are hard to segment because of low soft-tissue contrast, imaging artifacts, respiratory motion, and large treatment induced intra-thoracic anatomic changes. Hence, we developed a novel Patient-specific Anatomic Context and Shape prior or PACS-aware 3D recurrent registration-segmentation network for longitudinal thoracic CBCT segmentation. Segmentation and registration networks were concurrently trained in an end-to-end framework and implemente…
Face hallucination is a domain-specific super-resolution problem with the goal to generate high-resolution (HR) faces from low-resolution (LR) input images. In contrast to existing methods that often learn a single patch-to-patch mapping from LR to HR images and are regardless of the contextual interdependency between patches, we propose a novel Attention-aware Face Hallucination (Attention-FH) framework which resorts to deep reinforcement learning for sequentially discovering attended patches and then performing the facial part enhancement by fully exploiting the global interdependency of the…
IRSTEA（法国国家环境与农业科技研究院）；UMR TETIS（TETIS联合研究单位）；LIRMM（蒙彼利埃计算机科学与机器人实验室）；Univ. of Montpellier（蒙彼利埃大学）；CIRAD（法国国际农业发展研究中心）
Recurrent Neural Networks (RNNs) can be seriously impacted by the initial parameters assignment, which may result in poor generalization performances on new unseen data. With the objective to tackle this crucial issue, in the context of RNN based classification, we propose a new supervised layer-wise pretraining strategy to initialize network parameters. The proposed approach leverages a data-aware strategy that sets up a taxonomy of classification problems automatically derived by the model behavior. To the best of our knowledge, despite the great interest in RNN-based classification, this is…
Department of Information Engineering, The Chinese University of Hong Kong（香港中文大学信息工程学系）；The Chinese University of Hong Kong（香港中文大学）；Department of Information Engineering（信息工程学系）
The problem of video object segmentation can become extremely challenging when multiple instances co-exist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing failures in tracking. In this study, we formulate a deep recurrent network that is capable of segmenting and tracking objects in video simultaneously by their temporal continuity, yet able to re-identify them when they re-appear after a prolonged occlusion. We combine both temporal propagation and re-identification functionalities into a single framework th…
Topology-Aware Wavelet Mamba for Airway Structure Segmentation in Postoperative Recurrent Nasopharyngeal Carcinoma CT Scans
School of Software Engineering, Sun Yat-sen University（中山大学软件工程学院）；School of Microelectronics, Shanghai University（上海大学微电子学院）；Electronic and Computer Engineering, The Hong Kong University of Science and Technology（香港科技大学电子与计算机工程系）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属瑞金医院）；Eye & ENT Hospital, Fudan University（复旦大学附属眼耳鼻喉科医院）
In this paper, we present a novel recurrent multi-view stereo network based on long short-term memory (LSTM) with adaptive aggregation, namely AA-RMVSNet. We firstly introduce an intra-view aggregation module to adaptively extract image features by using context-aware convolution and multi-scale aggregation, which efficiently improves the performance on challenging regions, such as thin objects and large low-textured surfaces. To overcome the difficulty of varying occlusion in complex scenes, we propose an inter-view cost volume aggregation module for adaptive pixel-wise view aggregation, whic…
Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection. But, they do not work well with objects of multiple scales. To overcome such a limitation, in this work, we propose a recurrent attentional convolutional-deconvolution network (RACDNN). Using spatial transformer and recurrent network units, RACDNN is able to iteratively attend to selected image sub-regions to perform saliency refinement progressively. Besides tackling the scale problem, RACDNN can also learn context-aware features from past iterations to enhance saliency refinement in future iteration…
We propose the Part-based Recurrent Multi-view Aggregation network(PREMA) to eliminate the detrimental effects of the practical view defects, such as insufficient view numbers, occlusions or background clutters, and also enhance the discriminative ability of shape representations. Inspired by the fact that human recognize an object mainly by its discriminant parts, we define the multi-view coherent part(MCP), a discriminant part reoccurring in different views. Our PREMA can reliably locate and effectively utilize MCPs to build robust shape representations. Comprehensively, we design a novel Re…
University of Padova（帕多瓦大学）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires knowledge about past motion, the environment and likely destination areas. In this context, multi-modality is a fundamental aspect and its effective modeling can be beneficial to any architecture. Inferring accurate trajectories is nevertheless challenging, due to the inherently uncertain nature of the future. To overcome these difficulties, recent models use different inputs and propose to model human intentions usin…
Old Dominion University（欧道明大学）；Jefferson Laboratory（杰斐逊实验室）
Efficient processing of large-scale time series data is an intricate problem in machine learning. Conventional sensor signal processing pipelines with hand engineered feature extraction often involve huge computational cost with high dimensional data. Deep recurrent neural networks have shown promise in automated feature learning for improved time-series processing. However, generic deep recurrent models grow in scale and depth with increased complexity of the data. This is particularly challenging in presence of high dimensional data with temporal and spatial characteristics. Consequently, th…
