用三角一致性约束提升光流估计，无需额外标注且适配多种场景。
Triangular Consistency as a Universal Constraint for Learning Optical Flow
- 通过组合两组光流生成第三组，强制三者几何一致。
- 在监督、无监督及迁移学习中均实现稳定性能提升。
- 适用于图像对、多帧视频和合成数据增强，可即插即用。
我们提出三角一致性作为光流学习的普适性约束，该约束与网络结构、监督方式和数据集无关，适用于图像对和多帧场景。其核心思想是通过组合两组光流推导出第三组，并强制三者间的一致性。这种组合可源于：(i) 图像对，产生循环一致性；(ii) 多个视频帧，通过时间链传递长程运动信息；(iii) 图像对结合可控合成变换，用于数据增强。该方法计算开销极低，无需额外标注。由于直接基于光流几何性质推导，不依赖模型假设，可作为通用的“即插即用”组件。实验表明，其在监督、无监督和迁移学习设置下均带来持续性能提升。
原文摘要 · Abstract (English)
We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both image-pair and multi-frame settings. This simple but powerful constraint is to compose two flows to induce a third flow and enforce consistency among the three. The composed flows may arise from (i) image pairs, yielding cycle consistency; (ii) multiple video frames, producing longer-range motion through temporal chaining; or (iii) image pairs combined with controlled synthetic transformations, which becomes data augmentation. This triangular consistency introduces negligible computational overhead and requires no additional annotations. Since it is derived directly from the geometry of optical flow, it does not rely on model-specific assumptions and serves as a ``universal'' plug-and-play component for optical flow training. Experiments show consistent improvement across supervised, unsupervised, and transfer learning settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。