A dense long-term point tracker decouples flow quality estimation from optical flow computation, reaching accuracy comparable to state-of-the-art sparse trackers while providing dense coverage and a plug-and-play interface to arbitrary optical flow methods.
Tracking Everything Everywhere All at Once
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. Prior optical flow or particle video tracking algorithms typically operate within limited temporal windows, struggling to track through occlusions and maintain global consistency of estimated motion trajectories. We propose a complete and globally consistent motion representation, dubbed OmniMotion, that allows for accurate, full-length motion estimation of every pixel in a video. OmniMotion represents a video using a quasi-3D canonical volume and performs pixel-wise tracking via bijections between local and canonical space. This representation allows us to ensure global consistency, track through occlusions, and model any combination of camera and object motion. Extensive evaluations on the TAP-Vid benchmark and real-world footage show that our approach outperforms prior state-of-the-art methods by a large margin both quantitatively and qualitatively. See our project page for more results: http://omnimotion.github.io/
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation
A dense long-term point tracker decouples flow quality estimation from optical flow computation, reaching accuracy comparable to state-of-the-art sparse trackers while providing dense coverage and a plug-and-play interface to arbitrary optical flow methods.