arXiv：cs.LG· Luping Liu, Bingyi Kang, Yifan Wang, Dong Xu·· 3 小时前
FreeMatching：突破时空先验的通用稠密对应匹配框架
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
AI 导读
FreeMatching 将生成式与语义基础表征结合，并引入经典数据集、跟踪视频与合成场景的异构监督，实现跨图像编辑与参考引导生成（IEG）的保身份稠密对应匹配，被 NeurIPS 2026 接收。单个模型在困难的 IEG 图像对上大幅提升匹配质量，同时在经典基准上保持竞争力，还可作为评估身份保持的量化指标，其分数与人类判断相关。代码已开源。
正文
Abstract:Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry. While effective for classical tasks, these assumptions break down in image editing and reference-guided generation (IEG), where transformations can preserve visual identity while breaking physical continuity. To establish identity-preserving correspondence across such transformations, we introduce FreeMatching, a generalizable framework combining generative and semantic foundation representations with heterogeneous supervision from classical datasets, tracked videos, and synthetic scenes. Teacher-guided iterative refinement further improves correspondence in IEG without dense correspondence annotations. Experimentally, a single FreeMatching model substantially improves correspondence quality on challenging IEG image pairs while retaining competitive performance on classical benchmarks. Furthermore, we demonstrate its utility as a quantitative metric for evaluating identity preservation, with scores that correlate with human judgment. The code is available at this https URL.
| Comments: | Accepted at NeurIPS 2026. 24 pages, 7 figures, including appendices |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.12421 [cs.CV] |
| (or arXiv:2610.12421v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12421 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Luping Liu [view email]
[v1]
Thu, 8 Oct 2026 17:53:04 UTC (24,051 KB)
来源：arXiv：cs.LG · arxiv.org