Papers › CoTracker: It is Better to Track Together

CoTracker: It is Better to Track Together

14 Jul 2023arXiv:2307.07635archive 2025-07-28

Nikita Karaev, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht

We introduce CoTracker, a transformer-based model that tracks a large number of 2D points in long video sequences. Differently from most existing approaches that track points independently, CoTracker tracks them jointly, accounting for their dependencies. We show that joint tracking significantly improves tracking accuracy and robustness, and allows CoTracker to track occluded points and points outside of the camera view. We also introduce several innovations for this class of trackers, including using token proxies that significantly improve memory efficiency and allow CoTracker to track 70k points jointly and simultaneously at inference on a single GPU. CoTracker is an online algorithm that operates causally on short windows. However, it is trained utilizing unrolled windows as a recurrent network, maintaining tracks for long periods of time even when points are occluded or leave the field of view. Quantitatively, CoTracker substantially outperforms prior trackers on standard point-tracking benchmarks.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

facebookresearch/co-tracker officialmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos (arXiv:2410.11831; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
large-trajectory-model/atm mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Any-point Trajectory Modeling for Policy Learning (arXiv:2401.00025; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object TrackingOptical Flow EstimationPoint Trackingmotion prediction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Tracking TAP-Vid-DAVIS CoTracker Average Jaccard 65.9 #3 of 3 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS CoTracker Average PCK 79.4 #3 of 3 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS CoTracker Occlusion Accuracy 89.9 #3 of 3 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS-First CoTracker Average Jaccard 62.2 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS-First CoTracker Average PCK 75.7 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS-First CoTracker Occlusion Accuracy 89.3 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics-First CoTracker Average Jaccard 48.8 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics-First CoTracker Average PCK 64.5 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics-First CoTracker Occlusion Accuracy 85.8 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections