CoTracker3: Simpler and Better Point Tracking by Pseudo-Labeling Real Videos

By Nikita Karaev, Yuri Makarov, Jianyuan Wang, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht. IEEE International Conference on Computer Vision, 2025

309 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/32f48039871769be3290c625340c807d181f95aa

Citations in the corpus

• VGGT: Visual Geometry Grounded Transformer (2025, unknown): “CoTracker [37, 38] utilized correlations between different points to track through occlusions, while DOT [41] enabled dense tracking through occlusions.”