Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements. To alleviate this, the state-of-the-art framework RAFT gradually improves its prediction quality by using a large number of iterative refinements, achieving remarkable performance but introducing linearly increasing inference time. To enable both high accuracy and efficiency, we completely revamp the dominant flow regression pipeline by reformulating optical flow as a global matching problem, which identifies the correspondences by directly comparing feature similarities. Specifically, we propose a GMFlow framework, which consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. We further introduce a refinement step that reuses GMFlow at higher feature resolution for residual flow prediction. Our new framework outperforms 31-refinements RAFT on the challenging Sintel benchmark, while using only one refinement and running faster, suggesting a new paradigm for accurate and efficient optical flow estimation. Code is available at https://github.com/haofeixu/gmflow.
Rethinking Dense Optical Flow without Test-Time Scaling
Visual and Spatial AI Lab（视觉与空间人工智能实验室）；VCCM Section College of PVFA（VCCM学院光电工程学院）；Department of ECEN（电子工程系）；Department of CSCE（计算机科学与工程系）；Texas A&M University（德克萨斯A&M大学）
FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow
Department of Computer Engineering and KUIS AI Center, Koç University, Istanbul, Turkey（计算机工程系和KUIS人工智能中心，科克大学，伊斯坦布尔，土耳其）；Department of Computer Science and Engineering (DISI), University of Bologna, Italy（计算机科学与工程系（DISI），博洛尼亚大学，意大利）
SIGMA: Scale-Invariant Global Sparse Shape Matching
Technical University of Munich（慕尼黑工业大学）；University of Bonn（波恩大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；University of Siegen（锡根大学）；University of Oxford（牛津大学）
MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement
Embedded Deep Learning and Visual Analysis Laboratory, College of Future Information Technology, Fudan University（嵌入式深度学习与视觉分析实验室，未来信息技术学院，复旦大学）；Key Laboratory for Information Science of Electromagnetic Waves, Ministry of Education, Fudan University（电磁波信息科学重点实验室，教育部，复旦大学）
Fully Parallel Architecture for Semi-global Stereo Matching with Refined Rank Method
Shanghai Research Institute of Microelectronics (SHRIME), Peking University（北京大学上海微电子研究院）；School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）
QUIZ: An Arbitrary Volumetric Point Matching Method for Medical Image Registration
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Guangdong Medical University（广东医科大学）
Exploiting Global Camera Network Constraints for Unsupervised Video Person Re-identification
Hunan University（湖南大学）；National Engineering Laboratory for Robot Visual Perception and Control Technology（机器人视觉感知与控制技术国家工程实验室）；University of California, Riverside（加州大学河滨分校）
Structured Set Matching Networks for One-Shot Part Labeling
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Semantic Machines（语义机器公司）；University of Washington（华盛顿大学）
图表通常描述复杂的现象，并作为视觉和文本推理的良好测试平台。然而，使用自然图像理解方法来理解图需要大量的图训练数据集，这是非常难以获得的。相反，这可以作为标记图、图像或两者之间的匹配问题来解决。这个问题是非常具有挑战性的，因为缺乏显着的颜色和纹理呈现局部线索模糊，需要全局推理。我们考虑一次性部分标记的问题：在目标图像中标记对象的多个部分，仅给出该类别的单个源图像。对于这个集合到集合的匹配问题，我们引入了结构化集合匹配网络（SSMN），这是一种结合了卷积神经网络的结构化预测模型。使用全局归一化来训练SSMN，以最大化对应元素之间的局部匹配分数和所有匹配元素之间的全局一致性分数，同时还强制执行两个集合之间的匹配约束。SSMN在三个标签传输场景中的表现明显优于几个强大的基线：在200多个类别的新图表数据集上评估的图表到图表;在Pascal Part Dataset之上构建的数据集上评估的图像到图像;以及在这些数据集之间传输标签时评估的图像到图表。
BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration
Nantong University（南通大学）；Nanyang Technological University（南洋理工大学）；Nanjing University（南京大学）；Nanjing University of Science and Technology（南京理工大学）；Southeast University（东南大学）
LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching
Australian Centre for Robotics (ACFR), School of Aerospace, Mechanical and Mechatronic Engineering (AMME), Faculty of Engineering, The University of Sydney（悉尼大学工程学院航空航天、机械与机电工程学院澳大利亚机器人中心（ACFR））
Decomposed Global Optimization for Robust Point Matching with Low-Dimensional Branching
Department of Computer Science, Changzhi University, Changzhi, Shanxi, China, 046011（计算机科学系，长治大学）；School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China（计算机科学与技术学院，哈尔滨工业大学）
FedHPro: Federated Hyper-Prototype Learning via Gradient Matching
School of Computing and Information Technology, University of Wollongong, Wollongong, Australia（计算机与信息科技学院，沃尔灵戈大学，澳大利亚）；School of Computing and Information Systems, Singapore Management University, Singapore, Singapore（计算机与信息系统学院，新加坡管理大学，新加坡）；Monash University, Australia（莫纳什大学，澳大利亚）；Macquarie University, Australia（麦考瑞大学，澳大利亚）；Beijing Institute of Technology, China（北京理工大学，中国）；La Trobe University, Australia（拉筹伯大学，澳大利亚）
FaSS-MVS -- Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-borne Monocular Imagery
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB)（弗劳恩霍夫光学技术、系统技术与图像利用研究所）；Fraunhofer Center for Machine Learning（弗劳恩霍夫机器学习中心）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）
