Chen Wang

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

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

08.01.2025 00:55 — 👍 0    🔁 0    💬 0    📌 0

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

(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

08.01.2025 00:55 — 👍 0    🔁 0    💬 1    📌 0

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

(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.

08.01.2025 00:55 — 👍 0    🔁 0    💬 1    📌 0

(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.

08.01.2025 00:54 — 👍 2    🔁 0    💬 1    📌 1

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

07.01.2025 04:29 — 👍 4    🔁 2    💬 1    📌 0