AINeutralarXiv – CS AI · Jun 196/10
🧠
Triangular Consistency as a Universal Constraint for Learning Optical Flow
Researchers propose triangular consistency as a universal constraint for training optical flow models that works across different network architectures, supervision types, and datasets. This geometry-based approach composes flows to enforce consistency without additional annotations or significant computational overhead, showing improvements in supervised, unsupervised, and transfer learning settings.