{"title":"DeMatch++:基于深度运动场分解和局部上下文聚合的双视图对应学习。","authors":"Shihua Zhang,Zizhuo Li,Jiayi Ma","doi":"10.1109/tpami.2025.3596598","DOIUrl":null,"url":null,"abstract":"Two-view correspondence learning has increasingly focused on the coherence and smoothness of motion fields between image pairs. Conventional methods either regularize the complexity of the field function at substantial computational expense, or apply local filters that prove ineffective for large scene disparities. In this paper, we present DeMatch++, a novel network drawing inspiration from Fourier decomposition principles that decomposes the motion field to retain its primary \"low-frequency\" and smooth components. This approach achieves implicit regularization with lower computational overhead while exhibiting inherent piecewise smoothness. Specifically, our method decomposes the noise-contaminated motion field into multiple linearly independent basis vectors, generating smooth sub-fields that preserve the main energy of the original field. These sub-fields facilitate the recovery of a cleaner motion field for precise vector derivation. Within this framework, we aggregate local context within each sub-field while enhancing global information across all sub-fields. We also employ a masked decomposition strategy that mitigates the influence of false matches, and construct a compact representation to suppress redundant sub-fields. The complete pipeline is formulated as a discrete learnable architecture, circumventing the need for dense field computation. Extensive experiments demonstrate that DeMatch++ outperforms state-of-the-art methods while maintaining computational efficiency and piecewise smoothness. The code and trained models are publicly available at https://github.com/SuhZhang/DeMatchPlus.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"31 1","pages":""},"PeriodicalIF":18.6000,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DeMatch++: Two-View Correspondence Learning Via Deep Motion Field Decomposition and Respective Local-Context Aggregation.\",\"authors\":\"Shihua Zhang,Zizhuo Li,Jiayi Ma\",\"doi\":\"10.1109/tpami.2025.3596598\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Two-view correspondence learning has increasingly focused on the coherence and smoothness of motion fields between image pairs. Conventional methods either regularize the complexity of the field function at substantial computational expense, or apply local filters that prove ineffective for large scene disparities. In this paper, we present DeMatch++, a novel network drawing inspiration from Fourier decomposition principles that decomposes the motion field to retain its primary \\\"low-frequency\\\" and smooth components. This approach achieves implicit regularization with lower computational overhead while exhibiting inherent piecewise smoothness. Specifically, our method decomposes the noise-contaminated motion field into multiple linearly independent basis vectors, generating smooth sub-fields that preserve the main energy of the original field. These sub-fields facilitate the recovery of a cleaner motion field for precise vector derivation. Within this framework, we aggregate local context within each sub-field while enhancing global information across all sub-fields. We also employ a masked decomposition strategy that mitigates the influence of false matches, and construct a compact representation to suppress redundant sub-fields. The complete pipeline is formulated as a discrete learnable architecture, circumventing the need for dense field computation. Extensive experiments demonstrate that DeMatch++ outperforms state-of-the-art methods while maintaining computational efficiency and piecewise smoothness. The code and trained models are publicly available at https://github.com/SuhZhang/DeMatchPlus.\",\"PeriodicalId\":13426,\"journal\":{\"name\":\"IEEE Transactions on Pattern Analysis and Machine Intelligence\",\"volume\":\"31 1\",\"pages\":\"\"},\"PeriodicalIF\":18.6000,\"publicationDate\":\"2025-08-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Pattern Analysis and Machine Intelligence\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1109/tpami.2025.3596598\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Pattern Analysis and Machine Intelligence","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/tpami.2025.3596598","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
DeMatch++: Two-View Correspondence Learning Via Deep Motion Field Decomposition and Respective Local-Context Aggregation.
Two-view correspondence learning has increasingly focused on the coherence and smoothness of motion fields between image pairs. Conventional methods either regularize the complexity of the field function at substantial computational expense, or apply local filters that prove ineffective for large scene disparities. In this paper, we present DeMatch++, a novel network drawing inspiration from Fourier decomposition principles that decomposes the motion field to retain its primary "low-frequency" and smooth components. This approach achieves implicit regularization with lower computational overhead while exhibiting inherent piecewise smoothness. Specifically, our method decomposes the noise-contaminated motion field into multiple linearly independent basis vectors, generating smooth sub-fields that preserve the main energy of the original field. These sub-fields facilitate the recovery of a cleaner motion field for precise vector derivation. Within this framework, we aggregate local context within each sub-field while enhancing global information across all sub-fields. We also employ a masked decomposition strategy that mitigates the influence of false matches, and construct a compact representation to suppress redundant sub-fields. The complete pipeline is formulated as a discrete learnable architecture, circumventing the need for dense field computation. Extensive experiments demonstrate that DeMatch++ outperforms state-of-the-art methods while maintaining computational efficiency and piecewise smoothness. The code and trained models are publicly available at https://github.com/SuhZhang/DeMatchPlus.
期刊介绍:
The IEEE Transactions on Pattern Analysis and Machine Intelligence publishes articles on all traditional areas of computer vision and image understanding, all traditional areas of pattern analysis and recognition, and selected areas of machine intelligence, with a particular emphasis on machine learning for pattern analysis. Areas such as techniques for visual search, document and handwriting analysis, medical image analysis, video and image sequence analysis, content-based retrieval of image and video, face and gesture recognition and relevant specialized hardware and/or software architectures are also covered.