da-flow-degradation-aware-optical-flow

【数据与研究】A single insight reframes optical flow in degraded video as correspondence matching via diffusion features: restoration models naturally encode degradation patterns while preserving geometry. Add temporal reasoning via cross-frame attention to enable zero-shot correspondence without task-specific training. Trigger: When matching pixels across corrupt…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准