Papers › PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking

27 Jul 2023ICCV 2023 1arXiv:2307.15055archive 2025-07-28

Yang Zheng, Adam W. Harley, Bokui Shen, Gordon Wetzstein, Leonidas J. Guibas

We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks. Our data and code are publicly available at: https://pointodyssey.com

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2307.15055")

Code

Syntology Ran 10 of 13 code samples harvested from 3 repositories linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 9 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 8 ran; community (archive-listed): 5 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

y-zheng18/point_odyssey officialmentioned on GitHubNOASSERTION report
aharley/pips2 mentioned on GitHubpytorchMIT report
aliciachenw/PIPsUS mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

13 samples harvested; 10 ran; 1 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
9ran
3unverified

Licence: 8 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

as_path y-zheng18/point_odyssey/utils/file_io.py official repository ran licence not identified · pointer only · 2cb7740d09d1d57c · report
farthest_point_sampling y-zheng18/point_odyssey/utils/gen_tracking.py official repository ran fingerprinted licence not identified · pointer only · b360fe44d7520e4a · report
get_calibration_matrix_K_from_blender y-zheng18/point_odyssey/render_animal.py official repository ran licence not identified · pointer only · 4f778b5ed0da9d1f · report
get_intrinsics y-zheng18/point_odyssey/render_single.py official repository ran licence not identified · pointer only · 0bc392e72f43660f · report
read_json y-zheng18/point_odyssey/utils/file_io.py official repository ran licence not identified · pointer only · 21dd9ba5d9e47a8f · report
read_obj_file y-zheng18/point_odyssey/render_animal.py official repository ran licence not identified · pointer only · ba4494dbb46634a4 · report
read_obj_file y-zheng18/point_odyssey/utils/gen_tracking.py official repository ran licence not identified · pointer only · cf0f39e1349d5322 · report
reprojection y-zheng18/point_odyssey/utils/gen_tracking.py official repository ran licence not identified · pointer only · 5bdab6524d5a227a · report
coords_grid aliciachenw/PIPsUS/nets/pipsUS.py community (archive-listed) ran · honoured contract MIT (permissive) · ea43be6c224959b1 · report
load aharley/pips2/saverloader.py community (archive-listed) ran MIT (permissive) · 7cc0ed613ecce873 · report
bilinear_sampler aliciachenw/PIPsUS/nets/pipsUS.py community (archive-listed) unverified MIT (permissive) · 1ac8cce613d98769 · report
fetch_optimizer aharley/pips2/finetune_highres.py community (archive-listed) unverified MIT (permissive) · 257df3eb14fc528b · report
read_mp4 aharley/pips2/datasets/exportdataset.py community (archive-listed) unverified MIT (permissive) · 7617204334d1d459 · report

Tasks

DiversityPoint Tracking

Datasets

Introduced by this paper, per the archive.

PointOdyssey

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Tracking PointOdyssey PIPs++ MTE 26.95 #1 of 2 Archive leaderboard report
Point Tracking PointOdyssey PIPs++ Survival 50.47 #1 of 2 Archive leaderboard report
Point Tracking PointOdyssey PIPs++ δ 33.64 #1 of 2 Archive leaderboard report
Point Tracking PointOdyssey PIPs+ Survival 49.88 #2 of 2 Archive leaderboard report
Point Tracking PointOdyssey PIPs+ δ 32.41 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid PIPs++ MTE 4.6 #1 of 1 Archive leaderboard report
Point Tracking TAP-Vid PIPs++ Survival 88.42 #1 of 1 Archive leaderboard report
Point Tracking TAP-Vid PIPs++ δ 63.45 #1 of 1 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