Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking

Benchmark Model Rank Results
point-tracking-on-tap-vid-rgb-stacking-query-first-256-256DiTracker (CoTracker3) (extra data)#2AJ: 0.748OA: 0.909delta_avg: 0.852
point-tracking-on-robotap-query-first-256-256DiTracker (CoTracker3) (extra data)#4AJ: 0.665OA: 0.9delta_avg: 0.787
point-tracking-on-tap-vid-davis-query-first-256-256DiTracker (CoTracker3) (extra data)#6AJ: 0.648OA: 0.89delta_avg: 0.78