Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting. Our method is based on a semantic segmentation model without lateral connections within the upsampling path. Such design ensures that the forecasting addresses only the most abstract features on a very coarse resolution. We further propose to express feature-to-feature forecasting with deformable convolutions. This increases the modelling power due to being able to represent different motion patterns within a single feature map. Experiments show that our models with deformable convolutions outperform their regular and dilated counterparts while minimally increasing the number of parameters. Our method achieves state of the art performance on the Cityscapes validation set when forecasting nine timesteps into the future.
École Polytechnique de Montréal（蒙特利尔理工学院）；CortAIx Thales（泰雷兹CortAIx研究院）；Inria（法国国家信息与自动化研究院）
Advanced Driver-Assistance Systems rely heavily on perception tasks such as semantic segmentation where images are captured from large field of view (FoV) cameras. State-of-the-art works have made considerable progress toward applying Convolutional Neural Network (CNN) to standard (rectilinear) images. However, the large FoV cameras used in autonomous vehicles produce fisheye images characterized by strong geometric distortion. This work demonstrates that a CNN trained on standard images can be readily adapted to fisheye images, which is crucial in real-world applications where time-consuming …
In this paper we propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. By jointly reasoning about these tasks, our holistic approach is more robust to occlusion as well as sparse data at range. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world, which is very efficient in terms of both memory and computation. Our experiments on a new very large scale dataset captured in several north american cities, show that we can outperform the …
Shanghai AI Lab（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）
Due to the complex and changing interactions in dynamic scenarios, motion forecasting is a challenging problem in autonomous driving. Most existing works exploit static road graphs to characterize scenarios and are limited in modeling evolving spatio-temporal dependencies in dynamic scenarios. In this paper, we resort to dynamic heterogeneous graphs to model the scenario. Various scenario components including vehicles (agents) and lanes, multi-type interactions, and their changes over time are jointly encoded. Furthermore, we design a novel heterogeneous graph convolutional recurrent network, …
Long-term complex activity recognition and localisation can be crucial for decision making in autonomous systems such as smart cars and surgical robots. Here we address the problem via a novel deformable, spatiotemporal scene graph approach, consisting of three main building blocks: (i) action tube detection, (ii) the modelling of the deformable geometry of parts, and (iii) a graph convolutional network. Firstly, action tubes are detected in a series of snippets. Next, a new 3D deformable RoI pooling layer is designed for learning the flexible, deformable geometry of the constituent action tub…
The spatio-temporal information among video sequences is significant for video super-resolution (SR). However, the spatio-temporal information cannot be fully used by existing video SR methods since spatial feature extraction and temporal motion compensation are usually performed sequentially. In this paper, we propose a deformable 3D convolution network (D3Dnet) to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR. Specifically, we introduce deformable 3D convolution (D3D) to integrate deformable convolution with 3D convolution, obtaining both supe…
Mines ParisTech（巴黎矿业学院）；Facebook AI Research（脸书人工智能研究院）；Stanford University（斯坦福大学）
We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points, and applied to the input points close to them. Its capacity to use any number of kernel points gives KPConv more flexibility than fixed grid convolutions. Furthermore, these locations are continuous in space and can be learned by the network. Therefore, KPConv can be extended to deformable convolutions that learn to adapt kernel points to local geometry. Tha…
Discriminative Correlation Filter (DCF) based methods have shown competitive performance on tracking benchmarks in recent years. Generally, DCF based trackers learn a rigid appearance model of the target. However, this reliance on a single rigid appearance model is insufficient in situations where the target undergoes non-rigid transformations. In this paper, we propose a unified formulation for learning a deformable convolution filter. In our framework, the deformable filter is represented as a linear combination of sub-filters. Both the sub-filter coefficients and their relative locations ar…
Ocean University of China（中国海洋大学）；Harbin Institute of Technology（哈尔滨工业大学）
In recent years, crowd counting has become an important issue in computer vision. In most methods, the density maps are generated by convolving with a Gaussian kernel from the ground-truth dot maps which are marked around the center of human heads. Due to the fixed geometric structures in CNNs and indistinct head-scale information, the head features are obtained incompletely. Deformable convolution is proposed to exploit the scale-adaptive capabilities for CNN features in the heads. By learning the coordinate offsets of the sampling points, it is tractable to improve the ability to adjust the …
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Handwritten Text Recognition (HTR) in free-layout pages is a challenging image understanding task that can provide a relevant boost to the digitization of handwritten documents and reuse of their content. The task becomes even more challenging when dealing with historical documents due to the variability of the writing style and degradation of the page quality. State-of-the-art HTR approaches typically couple recurrent structures for sequence modeling with Convolutional Neural Networks for visual feature extraction. Since convolutional kernels are defined on fixed grids and focus on all input …
SPDCN: Strip-based Deformable Convolutional Network for Steel Surface Defect Segmentation
School of Artificial Intelligence, Jiangxi Normal University（江西师范大学人工智能学院）；Jiangxi Provincial Key Laboratory of Intelligent Information Processing and Affective Computing（江西省智能信息处理与情感计算重点实验室）
Fuzhou University（福州大学）；Tencent AI Lab（腾讯人工智能实验室）；Jiangnan University（江南大学）；South China University of Technology（华南理工大学）；City University of Hong Kong（香港城市大学）
The tracking-by-detection framework receives growing attentions through the integration with the Convolutional Neural Networks (CNNs). Existing tracking-by-detection based methods, however, fail to track objects with severe appearance variations. This is because the traditional convolutional operation is performed on fixed grids, and thus may not be able to find the correct response while the object is changing pose or under varying environmental conditions. In this paper, we propose a deformable convolution layer to enrich the target appearance representations in the tracking-by-detection fra…
University of Toronto（多伦多大学）；Uber Advanced Technologies Group（优步先进技术集团）
Point clouds are the native output of many real-world 3D sensors. To borrow the success of 2D convolutional network architectures, a majority of popular 3D perception models voxelize the points, which can result in a loss of local geometric details that cannot be recovered. In this paper, we propose a novel learnable convolution layer for processing 3D point cloud data directly. Instead of discretizing points into fixed voxels, we deform our learnable 3D filters to match with the point cloud shape. We propose to combine voxelized backbone networks with our deformable filter layer at 1) the net…
LDConv: Linear deformable convolution for improving convolutional neural networks
College of Computer and Information Science, Chongqing Normal University（重庆师范大学计算机与信息科学学院）；Chongqing Engineering Research Center of Educational Big Data Intelligent Perception and Application（重庆教育大数据智能感知与应用工程研究中心）；College of Electronic and Information Engineering, Southwest University（西南大学电子信息工程学院）
Chongqing University of Posts and Telecommunications（重庆邮电大学）；Chongqing University（重庆大学）
Most existing deep-learning-based single image dynamic scene blind deblurring (SIDSBD) methods usually design deep networks to directly remove the spatially-variant motion blurs from one inputted motion blurred image, without blur kernels estimation. In this paper, inspired by the Projective Motion Path Blur (PMPB) model and deformable convolution, we propose a novel constrained deformable convolutional network (CDCN) for efficient single image dynamic scene blind deblurring, which simultaneously achieves accurate spatially-variant motion blur kernels estimation and the high-quality image rest…
Enhanced Deformable Convolution with Center-invariant Offset and Edge-aware Mask
Beihang University（北京航空航天大学）；Shanghai Academy of Spaceflight Technology（上海航天技术研究院）；Shanghai Radio Equipment Research Institute（上海无线电设备研究所）；Cardiff University（卡迪夫大学）；Shenzhen University（深圳大学）；Sun Yat-sen University（中山大学）；Lancaster University（兰卡斯特大学）
University of Electronic Science and Technology of China（电子科技大学）
Recently, scene text recognition methods based on deep learning have sprung up in computer vision area. The existing methods achieved great performances, but the recognition of irregular text is still challenging due to the various shapes and distorted patterns. Consider that at the time of reading words in the real world, normally we will not rectify it in our mind but adjust our focus and visual fields. Similarly, through utilizing deformable convolutional layers whose geometric structures are adjustable, we present an enhanced recognition network without the steps of rectification to deal w…
DTC: A Deformable Transposed Convolution Module for Medical Image Segmentation
Department of Health Outcomes and Biomedical Informatics, University of Florida（健康结果与生物医学信息学系，佛罗里达大学）；Regenstrief Institue, Indiana University, IU Health（Regenstrief研究所，印第安纳大学，IU健康）
Video frame interpolation aims at synthesizing intermediate frames from nearby source frames while maintaining spatial and temporal consistencies. The existing deep-learning-based video frame interpolation methods can be roughly divided into two categories: flow-based methods and kernel-based methods. The performance of flow-based methods is often jeopardized by the inaccuracy of flow map estimation due to oversimplified motion models, while that of kernel-based methods tends to be constrained by the rigidity of kernel shape. To address these performance-limiting issues, a novel mechanism name…
Deformable part models (DPMs) and convolutional neural networks (CNNs) are two widely used tools for visual recognition. They are typically viewed as distinct approaches: DPMs are graphical models (Markov random fields), while CNNs are "black-box" non-linear classifiers. In this paper, we show that a DPM can be formulated as a CNN, thus providing a novel synthesis of the two ideas. Our construction involves unrolling the DPM inference algorithm and mapping each step to an equivalent (and at times novel) CNN layer. From this perspective, it becomes natural to replace the standard image features…
Shape deformation of targets in SAR image due to random orientation and partial information loss caused by occlusion of the radar signal, is an essential challenge in SAR ship detection. In this paper, we propose a data augmentation method to train a deep network that is robust to partial information loss within the targets. Taking advantage of ground-truth annotations for bounding box and instance segmentation mask, we present a simple and effective pipeline to simulate information loss on targets in instance-level, while preserving contextual information. Furthermore, we adopt deformable con…
Nanjing University of Posts and Telecommunications（南京邮电大学）；University of Trento（特伦托大学）；Wuhan University（武汉大学）
Learning to generate natural scenes has always been a daunting task in computer vision. This is even more laborious when generating images with very different views. When the views are very different, the view fields have little overlap or objects are occluded, leading the task very challenging. In this paper, we propose to use Generative Adversarial Networks(GANs) based on a deformable convolution and attention mechanism to solve the problem of cross-view image synthesis (see Fig.1). It is difficult to understand and transform scenes appearance and semantic information from another view, thus…
Shanghai Jiao Tong University（上海交通大学）；SJTU-ParisTech Elite Institute of Technology（上海交通大学-巴黎高科卓越工程学院）
Understanding the surrounding environment of the vehicle is still one of the challenges for autonomous driving. This paper addresses 360-degree road scene semantic segmentation using surround view cameras, which are widely equipped in existing production cars. First, in order to address large distortion problem in the fisheye images, Restricted Deformable Convolution (RDC) is proposed for semantic segmentation, which can effectively model geometric transformations by learning the shapes of convolutional filters conditioned on the input feature map. Second, in order to obtain a large-scale trai…
Nanyang Technological University（南洋理工大学）；Applied Research Center, Tencent PCG（腾讯PCG应用研究中心）；The Chinese University of Hong Kong（香港中文大学）；SIAT – SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院——商汤科技联合实验室）
Deformable convolution, originally proposed for the adaptation to geometric variations of objects, has recently shown compelling performance in aligning multiple frames and is increasingly adopted for video super-resolution. Despite its remarkable performance, its underlying mechanism for alignment remains unclear. In this study, we carefully investigate the relation between deformable alignment and the classic flow-based alignment. We show that deformable convolution can be decomposed into a combination of spatial warping and convolution. This decomposition reveals the commonality of deformab…
Mathematical Theory of Intelligent Systems of Moscow State University（莫斯科国立大学智能系统数学理论）
This article provides next step towards solving speed bottleneck of any system that intensively uses convolutions operations (e.g. CNN). Method described in the article is applied on deformable part models (DPM) algorithm. Method described here is based on multidimensional tensors and provides efficient tradeoff between DPM performance and accuracy. Experiments on various databases, including Pascal VOC, show that the proposed method allows decreasing a number of convolutions up to 4.5 times compared with DPM v.5, while maintaining similar accuracy. If insignificant accuracy degradation is all…
Sejong University（世宗大学）；The Australian National University（澳大利亚国立大学）；Data61-CSIRO（Data61-联邦科学与工业研究组织）；University of Technology Sydney（悉尼科技大学）
Salient Object Detection (SOD) domain using RGB-D data has lately emerged with some current models' adequately precise results. However, they have restrained generalization abilities and intensive computational complexity. In this paper, inspired by the best background/foreground separation abilities of deformable convolutions, we employ them in our Densely Deformable Network (DDNet) to achieve efficient SOD. The salient regions from densely deformable convolutions are further refined using transposed convolutions to optimally generate the saliency maps. Quantitative and qualitative evaluation…
Xidian University（西安电子科技大学）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Northwestern Polytechnical University（西北工业大学）
In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos. Instead of aligning frames in a pairwise manner, the deformable convolution can process multiple frames…
University at Buffalo（布法罗大学）；Beihang University（北京航空航天大学）；Kwai Inc.（快手公司）
In recent years, deep learning has dominated progress in the field of medical image analysis. We find however, that the ability of current deep learning approaches to represent the complex geometric structures of many medical images is insufficient. One limitation is that deep learning models require a tremendous amount of data, and it is very difficult to obtain a sufficient amount with the necessary detail. A second limitation is that there are underlying features of these medical images that are well established, but the black-box nature of existing convolutional neural networks (CNNs) do n…
Twin Deformable Point Convolutions for Point Cloud Semantic Segmentation in Remote Sensing Scenes
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）
University of Chinese Academy of Science（中国科学院大学）；Peking University（北京大学）；University of California, Berkeley（加州大学伯克利分校）
FPGAs provide a flexible and efficient platform to accelerate rapidly-changing algorithms for computer vision. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, including object detection and instance segmentation, have not been adequately addressed. Compared with image classification, detection problems are more sensitive to the spatial variance of objects, and therefore, require specialized convolutions to aggregate spatial information. To address this, recent work proposes dynamic deformable convolution to augment regular co…
Thales（泰雷兹集团）；Thales Digital Solutions（泰雷兹数字解决方案公司）；INRIA（法国国家信息与自动化研究所）
Conventional convolution neural networks (CNNs) trained on narrow Field-of-View (FoV) images are the state-of-the-art approaches for object recognition tasks. Some methods proposed the adaptation of CNNs to ultra-wide FoV images by learning deformable kernels. However, they are limited by the Euclidean geometry and their accuracy degrades under strong distortions caused by fisheye projections. In this work, we demonstrate that learning the shape of convolution kernels in non-Euclidean spaces is better than existing deformable kernel methods. In particular, we propose a new approach that learns…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）
Deep learning convolutional neural networks have proved to be a powerful tool for MRI analysis. In current work, we explore the potential of the deformable convolutional deep neural network layers for MRI data classification. We propose new 3D deformable convolutions(d-convolutions), implement them in VoxResNet architecture and apply for structural MRI data classification. We show that 3D d-convolutions outperform standard ones and are effective for unprocessed 3D MR images being robust to particular geometrical properties of the data. Firstly proposed dVoxResNet architecture exhibits high pot…
Many deep learning based methods are designed to remove non-uniform (spatially variant) motion blur caused by object motion and camera shake without knowing the blur kernel. Some methods directly output the latent sharp image in one stage, while others utilize a multi-stage strategy (\eg multi-scale, multi-patch, or multi-temporal) to gradually restore the sharp image. However, these methods have the following two main issues: 1) The computational cost of multi-stage is high; 2) The same convolution kernel is applied in different regions, which is not an ideal choice for non-uniform blur. Henc…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content. To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through inc…
Shape reconstruction of deformable organs from two-dimensional X-ray images is a key technology for image-guided intervention. In this paper, we propose an image-to-graph convolutional network (IGCN) for deformable shape reconstruction from a single-viewpoint projection image. The IGCN learns relationship between shape/deformation variability and the deep image features based on a deformation mapping scheme. In experiments targeted to the respiratory motion of abdominal organs, we confirmed the proposed framework with a regularized loss function can reconstruct liver shapes from a single digit…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Research AI（IBM 研究院人工智能部门）
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features followed by temporal modeling to capture long-term dependencies. While most recent papers have focused on the latter (long-temporal modeling), here, we focus on producing features capable of modeling fine-grained motion more efficiently. We propose a novel locally-consistent deformable convolution, which utilizes the change in receptive fields and enforces a local …
Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
Department of Physics, J.K. Institute of Science（J.K.科学研究所物理系）；World Scientific University（世界科学出版社大学）；University of Intelligent Studies（智能研究大学）；School of Computer and Electronic Information, Nanjing Normal University（南京师范大学计算机与电子信息学院）
Despite receiving significant attention from the research community, the task of segmenting and tracking objects in monocular videos still has much room for improvement. Existing works have simultaneously justified the efficacy of dilated and deformable convolutions for various image-level segmentation tasks. This gives reason to believe that 3D extensions of such convolutions should also yield performance improvements for video-level segmentation tasks. However, this aspect has not yet been explored thoroughly in existing literature. In this paper, we propose Dynamic Dilated Convolutions (D^2…
University of Bern（伯尔尼大学）；CentraleSupélec（中央理工-高等电力学院）；Université Paris-Saclay（巴黎-萨克雷大学）；Groupe Hospitalier Cochin-Hôtel Dieu（科钦-主宫医院集团）；Université Paris Descartes（巴黎笛卡尔大学）；TheraPanacea
Image registration and in particular deformable registration methods are pillars of medical imaging. Inspired by the recent advances in deep learning, we propose in this paper, a novel convolutional neural network architecture that couples linear and deformable registration within a unified architecture endowed with near real-time performance. Our framework is modular with respect to the global transformation component, as well as with respect to the similarity function while it guarantees smooth displacement fields. We evaluate the performance of our network on the challenging problem of MRI …
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Tsinghua University（清华大学）；Nanjing University（南京大学）；Shanghai AI Laboratory（上海人工智能实验室）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）
Peking University（北京大学）；Beijing Institute of Big Data Research（北京大数据研究院）；Massachusetts General Hospital（麻省总医院）
Pap smear testing has been widely used for detecting cervical cancers based on the morphology properties of cell nuclei in microscopic image. An accurate nuclei segmentation could thus improve the success rate of cervical cancer screening. In this work, a method of automated cervical nuclei segmentation using Deformable Multipath Ensemble Model (D-MEM) is proposed. The approach adopts a U-shaped convolutional network as a backbone network, in which dense blocks are used to transfer feature information more effectively. To increase the flexibility of the model, we then use deformable convolutio…
Font generation is a challenging problem especially for some writing systems that consist of a large number of characters and has attracted a lot of attention in recent years. However, existing methods for font generation are often in supervised learning. They require a large number of paired data, which is labor-intensive and expensive to collect. Besides, common image-to-image translation models often define style as the set of textures and colors, which cannot be directly applied to font generation. To address these problems, we propose novel deformable generative networks for unsupervised …
Graduate School of Informatics, Kyoto University（京都大学信息学研究科）；Graduate School of Medicine, Kyoto University（京都大学医学研究科）
Organ shape reconstruction based on a single-projection image during treatment has wide clinical scope, e.g., in image-guided radiotherapy and surgical guidance. We propose an image-to-graph convolutional network that achieves deformable registration of a 3D organ mesh for a single-viewpoint 2D projection image. This framework enables simultaneous training of two types of transformation: from the 2D projection image to a displacement map, and from the sampled per-vertex feature to a 3D displacement that satisfies the geometrical constraint of the mesh structure. Assuming application to radiati…
Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立高等物理、数学与信息学院）；New York University（纽约大学）；Facebook AI Research（Facebook人工智能研究院）
Anticipating future events is an important prerequisite towards intelligent behavior. Video forecasting has been studied as a proxy task towards this goal. Recent work has shown that to predict semantic segmentation of future frames, forecasting at the semantic level is more effective than forecasting RGB frames and then segmenting these. In this paper we consider the more challenging problem of future instance segmentation, which additionally segments out individual objects. To deal with a varying number of output labels per image, we develop a predictive model in the space of fixed-sized con…
Shanghai United Imaging Intelligence Co. Ltd（上海联影智能医疗科技有限公司）；Southern Medical University（南方医科大学）
In brain tumor diagnosis and surgical planning, segmentation of tumor regions and accurate analysis of surrounding normal tissues are necessary for physicians. Pathological variability often renders difficulty to register a well-labeled normal atlas to such images and to automatic segment/label surrounding normal brain tissues. In this paper, we propose a new registration approach that first segments brain tumor using a U-Net and then simulates missed normal tissues within the tumor region using a partial convolutional network. Then, a standard normal brain atlas image is registered onto such …
Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, detecting small-scaled pedestrians and occluded pedestrians remains a challenging problem. In this paper, we propose a pedestrian detection method with a couple-network to simultaneously address these two issues. One of the sub-networks, the gated multi-layer feature extraction sub-network, aims to adaptively generate discriminative features for pedestrian candidates in order to robustly detect pedestrians with large variations on scales. The second sub-networ…
