Learning Large Motion Estimation from Intermediate Representations with a High-Resolution Optical Flow Dataset Featuring Long-Range Dynamic Motion

work that integrates matching cost distillation and incremental time-step learning to refine cost volume estimation and stabilize training. Additionally, we leverage the distance map, which measures the distance from unmatched regions to their nearest matched pixels, improving occlusion handling. Our approach significantly enhances long-range optical flow estimation in high-resolution settings. Our datasets and code are available at https://github. com/Chohoonhee/RelayFlow-4K.