Local All-Pair Correspondence for Point Tracking
This addresses the challenge of robust point tracking in videos for computer vision applications, representing a strong specific gain rather than an incremental improvement.
The paper tackled the problem of tracking points across videos, which often fails in homogeneous or repetitive regions, by introducing LocoTrack, a model that uses local all-pair correspondences to achieve unmatched accuracy on TAP-Vid benchmarks and operates 6 times faster than the state-of-the-art.
We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely on local 2D correlation maps to establish correspondences from a point in the query image to a local region in the target image, which often struggle with homogeneous regions or repetitive features, leading to matching ambiguities. LocoTrack overcomes this challenge with a novel approach that utilizes all-pair correspondences across regions, i.e., local 4D correlation, to establish precise correspondences, with bidirectional correspondence and matching smoothness significantly enhancing robustness against ambiguities. We also incorporate a lightweight correlation encoder to enhance computational efficiency, and a compact Transformer architecture to integrate long-term temporal information. LocoTrack achieves unmatched accuracy on all TAP-Vid benchmarks and operates at a speed almost 6 times faster than the current state-of-the-art.