In this paper, we tackle the task of establishing dense visual correspondences between images containing objects of the same category. This is a challenging task due to large intra-class variations and a lack of dense pixel level annotations. We propose a convolutional neural network architecture, called adaptive neighbourhood consensus network (ANC-Net), that can be trained end-to-end with sparse key-point annotations, to handle this challenge. At the core of ANC-Net is our proposed non-isotropic 4D convolution kernel, which forms the building block for the adaptive neighbourhood consensus module for robust matching. We also introduce a simple and efficient multi-scale self-similarity module in ANC-Net to make the learned feature robust to intra-class variations. Furthermore, we propose a novel orthogonal loss that can enforce the one-to-one matching constraint. We thoroughly evaluate the effectiveness of our method on various benchmarks, where it substantially outperforms state-of-the-art methods.
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
École Normale Supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）；Czech Technical University in Prague（捷克布拉格技术大学）；Inria（法国国家信息与自动化研究所）；DeepMind
Zero-Shot Image Feature Consensus with Deep Functional Maps
PKU-WUHAN Institute for Artificial Intelligence（北京大学-武汉人工智能研究院）；Institute for AI, Peking University（北京大学人工智能研究院）；Department of Computer Science, Stanford University（斯坦福大学计算机科学系）
Progressive Correspondence Pruning by Consensus Learning
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）
MGCA-Net: Multi-Graph Contextual Attention Network for Two-View Correspondence Learning
College of Cyber Security, Jinan University, Guangzhou, China（广州大学网络安全学院）；Chongqing Key Laboratory of Image Cognition, College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China（重庆邮电大学计算机科学与技术学院）；Peng Cheng Laboratory, Shenzhen, China（鹏城实验室）；Department of Computer Science, City University of Hong Kong, Hong Kong, China（香港城市大学计算机科学系）
Hierarchical Consensus Network for Multiview Feature Learning
School of Information Science and Engineering, Lanzhou University（兰州大学信息科学与工程学院）；Australian Artificial Intelligence Institute, University of Technology Sydney（悉尼科技大学澳大利亚人工智能学院）
RANSAC Back to SOTA: A Two-stage Consensus Filtering for Real-time 3D Registration
School of Computer Science, Wuhan University（武汉大学计算机学院）；Hong Kong Polytechnic University（香港理工大学）；School of Remote Sensing and Information Engineering, Wuhan University（武汉大学遥感信息工程学院）
针对 RANSAC 在高外点率下迭代激增的问题，本文提出 TCF，通过长度、角度和距离一致性的两阶段滤波实现实时三维点云配准，并在 KITTI、ETH 上较 MAC 最高加速三个数量级。
GenReg: Deep Generative Method for Fast Point Cloud Registration
Image X Institute, University of Sydney（悉尼大学 Image X 研究所）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；University of Techonology Sydney（悉尼科技大学）；Jiangxi University of Finance and Economics（江西财经大学）；Xpeng（小鹏）
