While much progress has been made on the task of 3D point cloud registration, there still exists no learning-based method able to estimate the 6D pose of an object observed by a 2.5D sensor in a scene. The challenges of this scenario include the fact that most measurements are outliers depicting the object's surrounding context, and the mismatch between the complete 3D object model and its self-occluded observations.
We introduce the first deep learning framework capable of effectively handling this scenario. Our method consists of an instance segmentation module followed by a pose estimation one. It allows us to perform 3D registration in a one-shot manner, without requiring an expensive iterative procedure. We further develop an on-the-fly rendering-based training strategy that is both time- and memory-efficient. Our experiments evidence the superiority of our approach over the state-of-the-art traditional and learning-based 3D registration methods.
Detecting partially occluded objects is a difficult task. Our experimental results show that deep learning approaches, such as Faster R-CNN, are not robust at object detection under occlusion. Compositional convolutional neural networks (CompositionalNets) have been shown to be robust at classifying occluded objects by explicitly representing the object as a composition of parts. In this work, we propose to overcome two limitations of CompositionalNets which will enable them to detect partially occluded objects: 1) CompositionalNets, as well as other DCNN architectures, do not explicitly separ…
Fordham University Department of Computer Science（福特汉姆大学计算机科学系）
The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to aid in object recognition in biological vision. In this work, we attempt to add robustness into existing Region Proposal Network-Deep Convolutional Neural Network (RPN-DCNN) object detection networks through two distinct scene-based information fusion techniques. We present one algorithm under each methodology: the first operates prior to prediction, select…
Deformable surface tracking from monocular images is well-known to be under-constrained. Occlusions often make the task even more challenging, and can result in failure if the surface is not sufficiently textured. In this work, we explicitly address the problem of 3D reconstruction of poorly textured, occluded surfaces, proposing a framework based on a template-matching approach that scales dense robust features by a relevancy score. Our approach is extensively compared to current methods employing both local feature matching and dense template alignment. We test on standard datasets as well a…
Huazhong University of Science and Technology（华中科技大学）；Alibaba Group（阿里巴巴集团）；Cornell University（康奈尔大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Oxford（牛津大学）
Although deep learning methods have achieved advanced video object recognition performance in recent years, perceiving heavily occluded objects in a video is still a very challenging task. To promote the development of occlusion understanding, we collect a large-scale dataset called OVIS for video instance segmentation in the occluded scenario. OVIS consists of 296k high-quality instance masks and 901 occluded scenes. While our human vision systems can perceive those occluded objects by contextual reasoning and association, our experiments suggest that current video understanding systems canno…
Alibaba Group（阿里巴巴集团）；University of Copenhagen（哥本哈根大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Oxford（牛津大学）
Can our video understanding systems perceive objects when a heavy occlusion exists in a scene? To answer this question, we collect a large-scale dataset called OVIS for occluded video instance segmentation, that is, to simultaneously detect, segment, and track instances in occluded scenes. OVIS consists of 296k high-quality instance masks from 25 semantic categories, where object occlusions usually occur. While our human vision systems can understand those occluded instances by contextual reasoning and association, our experiments suggest that current video understanding systems cannot. On the…
While impressive progress has been achieved, video instance segmentation (VIS) methods with per-clip input often fail on challenging videos with occluded objects and crowded scenes. This is mainly because instance queries in these methods cannot encode well the discriminative embeddings of instances, making the query-based segmenter difficult to distinguish those `hard' instances. To address these issues, we propose to mine discriminative query embeddings (MDQE) to segment occluded instances on challenging videos. First, we initialize the positional embeddings and content features of object qu…
University College London（伦敦大学学院）；Adobe Systems（Adobe系统公司）
Discovering 3D arrangements of objects from single indoor images is important given its many applications including interior design, content creation, etc. Although heavily researched in the recent years, existing approaches break down under medium or heavy occlusion as the core object detection module starts failing in absence of directly visible cues. Instead, we take into account holistic contextual 3D information, exploiting the fact that objects in indoor scenes co-occur mostly in typical near-regular configurations. First, we use a neural network trained on real indoor annotated images t…
Digital Elevation models (DEM) are images having terrain information embedded into them. Using cognitive mapping concepts for DEM registration, has evolved from this basic idea of using the mapping between the space to objects and defining their relationships to form the basic landmarks that need to be marked, stored and manipulated in and about the environment or other candidate environments, namely, in our case, the DEMs. The progressive two-level encapsulation of methods of geo-spatial cognition includes landmark knowledge and layout knowledge and can be useful for DEM registration. Space-b…
RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity
Cornell University（康奈尔大学）；Kansas State University（堪萨斯州立大学）
Cleveland State University（克利夫兰州立大学）；Nanyang Technological University（南洋理工大学）；Wuhan University（武汉大学）；Beijing University of Technology（北京工业大学）；Brookhaven National Laboratory（布鲁克海文国家实验室）
The processing and recognition of geoscience images have wide applications. Most of existing researches focus on understanding the high-quality geoscience images by assuming that all the images are clear. However, in many real-world cases, the geoscience images might contain occlusions during the image acquisition. This problem actually implies the image inpainting problem in computer vision and multimedia. To the best of our knowledge, all the existing image inpainting algorithms learn to repair the occluded regions for a better visualization quality, they are excellent for natural images but…
Using image context is an effective approach for improving object detection. Previously proposed methods used contextual cues that rely on semantic or spatial information. In this work, we explore a different kind of contextual information: inner-scene similarity. We present the CISS (Context by Inner Scene Similarity) algorithm, which is based on the observation that two visually similar sub-image patches are likely to share semantic identities, especially when both appear in the same image. CISS uses base-scores provided by a base detector and performs as a post-detection stage. For each can…
While 3D-3D registration is traditionally tacked by optimization-based methods, recent work has shown that learning-based techniques could achieve faster and more robust results. In this context, however, only PRNet can handle the partial-to-partial registration scenario. Unfortunately, this is achieved at the cost of relying on an iterative procedure, with a complex network architecture. Here, we show that learning-based partial-to-partial registration can be achieved in a one-shot manner, jointly reducing network complexity and increasing registration accuracy. To this end, we propose an Opt…
A key step to driver safety is to observe the driver's activities with the face being a key step in this process to extracting information such as head pose, blink rate, yawns, talking to passenger which can then help derive higher level information such as distraction, drowsiness, intent, and where they are looking. In the context of driving safety, it is important for the system perform robust estimation under harsh lighting and occlusion but also be able to detect when the occlusion occurs so that information predicted from occluded parts of the face can be taken into account properly. This…
Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neural networks (DCNNs) have only limited robustness to partial occlusion. We overcome these limitations by unifying DCNNs with part-based models into Compositional Convolutional Neural Networks (CompositionalNets) - an interpretable deep architecture with innate robustness to partial occlusion. Specifically, we propose to replace the fully connected classification head of DCNNs with a differentiable compositional model …
Institute for Research in Fundamental Sciences (IPM)（基础科学研究所（IPM））
This study is concerned with the top-down visual processing benefit in the task of occluded object recognition. To this end, a psychophysical experiment is designed and carried out which aimed at investigating the effect of consistency of contextual information on the recognition of objects which are partially occluded. The results demonstrate the facilitative impact of consistent contextual clues on the task of object recognition in presence of occlusion.
Istituto Italiano di Tecnologia（意大利理工学院）；Politecnico di Milano（米兰理工大学）；University College London（伦敦大学学院）；University College London Hospital（伦敦大学学院医院）；University Hospital Leuven（鲁汶大学医院）；Istituto "Giannina Gaslini"（詹尼娜·加斯利尼研究所）；Scuola Superiore Sant’Anna（圣安娜高等学校）
In Twin-to-Twin Transfusion Syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the two fetuses. In the current practice, TTTS is treated surgically by closing abnormal anastomoses using laser ablation. This surgery is minimally invasive and relies on fetoscopy. Limited field of view makes anastomosis identification a challenging task for the surgeon. To tackle this challenge, we propose a learning-based framework for in-vivo fetoscopy frame registration for field-of-view expansion. The novelties of this framework relies on a learn…
In general, the problem of non-rigid registration is about matching two different scans of a dynamic object taken at two different points in time. These scans can undergo both rigid motions and non-rigid deformations. Since new parts of the model may come into view and other parts get occluded in between two scans, the region of overlap is a subset of both scans. In the most general setting, no prior template shape is given and no markers or explicit feature point correspondences are available. So, this case is a partial matching problem that takes into account the assumption that consequent s…
In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches to addressing this task have shown great success on synthetic datasets, we have observed them to fail in the presence of real-world data. We thus analyze the causes of these failures, which we trace back to the difference between the feature distributions of the source and target point clouds, and the sensitivity of the widely-used SVD-based loss function to the range of rotation between the two point clouds. We address the first challenge by introducing a new n…
University of North Carolina（北卡罗来纳大学）；Shanghai Jiao Tong University（上海交通大学）
Deformable image registration is fundamental to longitudinal and population analysis. Geometric alignment of the infant brain MR images is challenging, owing to rapid changes in image appearance in association with brain development. In this paper, we propose an infant-dedicated deep registration network that uses the auto-context strategy to gradually refine the deformation fields to obtain highly accurate correspondences. Instead of training multiple registration networks, our method estimates the deformation fields by invoking a single network multiple times for iterative deformation refine…
Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context
Engineering Research Center for Metallurgical Automation（冶金自动化工程研究中心）；Measurement Technology Ministry of Education, Wuhan University of Science（测量技术教育部武汉科技大学）；School of Information Management（信息管理学院）；Institute of Big Data（大数据研究院）；Digital Economy, Hubei University of Economics, Wuhan, 430205, China（数字经济，湖北经济学院，武汉，430205，中国）
State-of-the-art techniques proposed for 6D object pose recovery depend on occlusion-free point clouds to accurately register objects in 3D space. To reduce this dependency, we introduce a novel architecture called Iterative Hough Forest with Histogram of Control Points that is capable of estimating occluded and cluttered objects' 6D pose given a candidate 2D bounding box. Our Iterative Hough Forest is learnt using patches extracted only from the positive samples. These patches are represented with Histogram of Control Points (HoCP), a "scale-variant" implicit volumetric description, which we …
RCC Institute of Information Technology（RCC信息技术学院）；Jadavpur University（贾达普大学）
In this paper, we propose a robust 3D face recognition system which can handle pose as well as occlusions in real world. The system at first takes as input, a 3D range image, simultaneously registers it using ICP(Iterative Closest Point) algorithm. ICP used in this work, registers facial surfaces to a common model by minimizing distances between a probe model and a gallery model. However the performance of ICP relies heavily on the initial conditions. Hence, it is necessary to provide an initial registration, which will be improved iteratively and finally converge to the best alignment possibl…
Chongqing University（重庆大学）；Chongqing Medical University（重庆医科大学）；Sichuan Fine Arts Institute（四川美术学院）
Because of affected by weather conditions, camera pose and range, etc. Objects are usually small, blur, occluded and diverse pose in the images gathered from outdoor surveillance cameras or access control system. It is challenging and important to detect faces precisely for face recognition system in the field of public security. In this paper, we design a based on context modeling structure named Feature Hierarchy Encoder-Decoder Network for face detection(FHEDN), which can detect small, blur and occluded face with hierarchy by hierarchy from the end to the beginning likes encoder-decoder in …
School of Geospatial Engineering and Science, Sun Yat-Sen University（中山大学测绘科学与技术学院）；Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University（香港理工大学土地测量及地理资讯学系）；Changjiang River Scientific Research Institute (CRSRI)（长江水利委员会长江科学院）；Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院数字地球重点实验室）；Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)（南方海洋科学与工程广东省实验室（珠海））
Registration of unmanned aerial vehicle laser scanning (ULS) and ground light detection and ranging (LiDAR) point clouds in forests is critical to create a detailed representation of a forest structure and an accurate inversion of forest parameters. However, forest occlusion poses challenges for marker-based registration methods, and some marker-free automated registration methods have low efficiency due to the process of object (e.g., tree, crown) segmentation. Therefore, we use a divide-and-conquer strategy and propose an automated and efficient method to register ULS and ground LiDAR point …
Center for Visual Information Technology (CVIT), IIIT-Hyderabad（国际信息技术研究所（海得拉巴）视觉信息技术中心（CVIT））
Feature-based registration has been popular with a variety of features ranging from voxel intensity to Self-Similarity Context (SSC). In this paper, we examine the question on how features learnt using various Deep Learning (DL) frameworks can be used for deformable registration and whether this feature learning is necessary or not. We investigate the use of features learned by different DL methods in the current state-of-the-art discrete registration framework and analyze its performance on 2 publicly available datasets. We draw insights into the type of DL framework useful for feature learni…
Occluded Gait Recognition with Mixture of Experts: An Action Detection Perspective
School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；School of Computer Science and Technology, Beihang University（北京航空航天大学计算机科学与技术学院）；AI Lab, Lenovo Research（联想研究院人工智能实验室）
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Bournemouth University（伯恩茅斯大学）；Sun Yat-sen University（中山大学）
Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions. Their intrinsic problem is that they directly localize the joints based on visual information; however, the invisible joints are lack of that. In contrast to localization, our framework estimates the invisible joints from an inference perspective by proposing an Image-Guided Progressive GCN module which provides a comprehensive understanding of both image context and pose structure. Moreover, existing benchmarks contain …
Université de Nantes（南特大学）；CNRS（法国国家科学研究中心）；INSERM（法国国家健康与医学研究院）；l’institut du thorax（胸腔研究所）；CHU Nantes（南特大学附属医院）；SFR Santé（健康科学研究联合会）
Correlative microscopy aims at combining two or more modalities to gain more information than the one provided by one modality on the same biological structure. Registration is needed at different steps of correlative microscopies workflows. Biologists want to select the image content used for registration not to introduce bias in the correlation of unknown structures. Intensity-based methods might not allow this selection and might be too slow when the images are very large. We propose an approach based on point clouds created from selected content by the biologist. These point clouds may be …
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…
Imperial College London（帝国理工学院）；TheraPanacea；University of Oxford（牛津大学）；CentraleSupelec（中央高等电力学院）；INRIA（法国国家信息与自动化研究所）；Universite Paris-Saclay（巴黎萨克雷大学）
We propose a novel weakly supervised discriminative algorithm for learning context specific registration metrics as a linear combination of conventional similarity measures. Conventional metrics have been extensively used over the past two decades and therefore both their strengths and limitations are known. The challenge is to find the optimal relative weighting (or parameters) of different metrics forming the similarity measure of the registration algorithm. Hand-tuning these parameters would result in sub optimal solutions and quickly become infeasible as the number of metrics increases. Fu…
Image registration plays an important role in medical image analysis. Conventional optimization based methods provide an accurate estimation due to the iterative process at the cost of expensive computation. Deep learning methods such as learn-to-map are much faster but either iterative or coarse-to-fine approach is required to improve accuracy for handling large motions. In this work, we proposed to learn a registration optimizer via a multi-scale neural ODE model. The inference consists of iterative gradient updates similar to a conventional gradient descent optimizer but in a much faster wa…
Applications based on synergistic integration of optical imagery and LiDAR data are receiving a growing interest from the remote sensing community. However, a misaligned integration between these datasets may fail to fully profit the potential of both sensors. In this regard, an optimum fusion of optical imagery and LiDAR data requires an accurate registration. This is a complex problem since a versatile solution is still missing, especially when considering the context where data are collected at different times, from different platforms, under different acquisition configurations. This paper…
Amodal completion is a visual task that humans perform easily but which is difficult for computer vision algorithms. The aim is to segment those object boundaries which are occluded and hence invisible. This task is particularly challenging for deep neural networks because data is difficult to obtain and annotate. Therefore, we formulate amodal segmentation as an out-of-task and out-of-distribution generalization problem. Specifically, we replace the fully connected classifier in neural networks with a Bayesian generative model of the neural network features. The model is trained from non-occl…
MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院）；University of Twente（特文特大学）；University of Cambridge（剑桥大学）；University of Bath（巴斯大学）；Phigent Robotics（飞劲机器人公司）
Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoders
National Engineering Research Center for Robot Visual Perception and Control Technology, School of Artificial Intelligence and Robotics, Hunan University（国家机器人视觉感知与控制技术工程研究中心，人工智能与机器人学院，湖南大学）；School of Architecture and Art, Central South University（建筑与艺术学院，中南大学）；Department of Computer Science and Software Engineering, The University of Western Australia（计算机科学与软件工程系，西澳大学）
Image registration is a key component of various image processing operations which involve the analysis of different image data sets. Automatic image registration domains have witnessed the application of many intelligent methodologies over the past decade; however inability to properly model object shape as well as contextual information had limited the attainable accuracy. In this paper, we propose a framework for accurate feature shape modeling and adaptive resampling using advanced techniques such as Vector Machines, Cellular Neural Network (CNN), SIFT, coreset, and Cellular Automata. CNN …
Virginia Tech（弗吉尼亚理工大学）；Facebook（脸书）；National Tsing Hua University（国立清华大学）
We propose a method for converting a single RGB-D input image into a 3D photo - a multi-layer representation for novel view synthesis that contains hallucinated color and depth structures in regions occluded in the original view. We use a Layered Depth Image with explicit pixel connectivity as underlying representation, and present a learning-based inpainting model that synthesizes new local color-and-depth content into the occluded region in a spatial context-aware manner. The resulting 3D photos can be efficiently rendered with motion parallax using standard graphics engines. We validate the…
IMITATE: Image Registration with Context for unknown time frame recovery
Centre de Recherches en Cancérologie de Toulouse, INSERM UMR1037, Team RADOPT（图卢兹癌症研究中心，INSERM UMR1037，RADOPT团队）；Université de Toulouse（图卢兹大学）；Institut Universitaire du Cancer – Oncopole Claudius Régaud（癌症大学研究所 – 克劳迪乌斯·雷加德肿瘤中心）；Institut de Mathématiques de Toulouse (UMR 5219), CNRS, Université de Toulouse（图卢兹数学研究所（UMR 5219），CNRS，图卢兹大学）
Impact of Initialization on Intra-subject Pediatric Brain MR Image Registration: A Comparative Analysis between SyN ANTs and Deep Learning-Based Approaches
Polytechnique Montréal（蒙特利尔理工学院）；Ste-Justine Hospital University Centre（圣贾斯汀医院大学中心）；Université de Strasbourg（斯特拉斯堡大学）；CNRS（法国国家科学研究中心）
Spatially Covariant Image Registration with Text Prompts
College of Electrical and Information Engineering, Hunan University（湖南大学电气与信息工程学院）；Cornell University（康奈尔大学）；University of Pennsylvania（宾夕法尼亚大学）；New York University（纽约大学）；Shanghai Jiao Tong University（上海交通大学）
