Triangular Consistency as a Universal Constraint for Learning Optical Flow
This work provides a simple, universal plug-and-play constraint that enhances optical flow training across diverse settings, benefiting researchers and practitioners in motion estimation.
The paper introduces triangular consistency as a universal constraint for optical flow learning, applicable to various supervision types and settings. It consistently improves performance across supervised, unsupervised, and transfer learning scenarios with negligible computational overhead.
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.