iiinova — where your digital self keeps evolving

Chen Wang

@cwchenwang.bsky.social

Ph.D. student at UPenn, B.Eng and M.Eng from THU

Chen Wang @cwchenwang.bsky.social · 08/01/2025

(4/N) Project page: michaelszj.github.io/protracker/ Paper: arxiv.org/abs/2501.03220 Code: michaelszj.github.io/protracker/

michaelszj.github.io

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

000

Chen Wang @cwchenwang.bsky.social · 08/01/2025

(3/N)💡Protracker offers a probabilistic framework that combines information of different granularity and semantics, paving the way for new advancements in tracking any point. 🔍#PointTracking #ComputerVision

michaelszj.github.io

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

100

Chen Wang @cwchenwang.bsky.social · 08/01/2025

(2/N) This ensures to generate smooth and accurate trajectories. ProTracker achieves state-of-the-art performance among self-supervised methods across multiple benchmarks and enhanced robustness in challenging scenarios like occlusion, similar regions, and low-feature areas.

michaelszj.github.io

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

100

Chen Wang @cwchenwang.bsky.social · 08/01/2025

(1/N)🚀Introducing Protracker: Inspired by Kalman filter, we tackle point tracking with a robust probabilistic approach. 🌟Our method integrates multiple predictions from both optical flow and semantic correspondences in a unified framework with probabilistic fusion.

120

Reposted by Chen Wang

Zhenjun Zhao @ericzzj.bsky.social · 07/01/2025

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking Tingyang Zhang, @cwchenwang.bsky.social, @frankzydou.bsky.social, Qingzhe Gao, Jiahui Lei, Baoquan Chen, @lingjieliu.bsky.social arxiv.org/abs/2501.03220

142