[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy
Python · active 2025-06-25 → 2026-06-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 354 days from 2025-06-25 to 2026-06-13. Pushes: 26 total, peak 9 in a day. Pull requests: 5 total, peak 1 in a day. Issues: 31 total, peak 3 in a day. Comments: 41 total, peak 7 in a day. Stars: 458 total, peak 52 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| henry123-boy | 36 | 22 | 2 | 11 |
| bhack | 7 | 0 | 0 | 5 |
| sunshineinsandiego | 5 | 0 | 0 | 2 |
| okj-okj | 5 | 0 | 0 | 1 |
| cherubicXN | 4 | 4 | 0 | 0 |
| zzhang2816 | 3 | 0 | 0 | 2 |
| ewebgh33 | 3 | 0 | 0 | 3 |
| Hantao-Ye | 3 | 0 | 0 | 1 |
| Junxix | 2 | 0 | 0 | 1 |
| honglin-c | 2 | 0 | 0 | 1 |
| HarborC | 2 | 0 | 0 | 1 |
| polar-explorer | 2 | 0 | 0 | 0 |
| NicoloIacobone | 2 | 0 | 0 | 2 |
| JayKarhade | 1 | 0 | 0 | 1 |
| Luo-Yihang | 1 | 0 | 0 | 1 |
| jianingnz | 1 | 0 | 0 | 0 |
| XcloudFance | 1 | 0 | 0 | 1 |
| matthew-strong-ai | 1 | 0 | 0 | 1 |
| YJ-142150 | 1 | 0 | 0 | 0 |
| LiuhanChen-github | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#42jorel6662026-05-03 04:33Preprocessing input video twice during inference
- Issue#40LiuhanChen-github2026-01-21 08:37Envirement error
- Issue comment#24jwlarocque2025-12-28 18:02GPU requirements / CPU version availability
- Issue#39WuJH20012025-11-10 10:39Question about points tracking
- Issue#25Hantao-Ye2025-11-08 21:37pyceres==2.4 requirement
- Issue comment#25Hantao-Ye2025-11-08 21:37pyceres==2.4 requirement
- Issue#37jianingnz2025-10-08 04:41Scale of The Pointmap Output
- Issue comment#32pandayuanyu2025-10-07 02:57Out of Memory error when running on RTX 3060 (12GB)
- Pull request#26henry123-boy2025-09-26 17:15
- Issue comment#26henry123-boy2025-09-26 17:15added version restriction to pyceres
- Issue comment#16honglin-c2025-09-23 21:58Known initial point cloud
- Pull request#36skoppula2025-09-21 17:15
- Issue comment#29Ysc-shark2025-09-18 05:03module 'utils3d.torch' has no attribute 'depth_edge'
- Issue comment#16Luo-Yihang2025-09-14 09:58Known initial point cloud
- Issue#35okj-okj2025-09-11 04:18After a certain amount of time colored dots loose their position and mess up track
- Issue comment#34okj-okj2025-09-11 04:10RuntimeError: output with shape [101, 336, 588] doesn't match the broadcast shape [101, 101, 336, 588]
- Issue#34okj-okj2025-09-11 04:10RuntimeError: output with shape [101, 336, 588] doesn't match the broadcast shape [101, 101, 336, 588]
- Issue comment#29NicoloIacobone2025-09-10 17:48module 'utils3d.torch' has no attribute 'depth_edge'
- Issue comment#34XcloudFance2025-09-09 11:35RuntimeError: output with shape [101, 336, 588] doesn't match the broadcast shape [101, 101, 336, 588]
- Issue#34okj-okj2025-09-09 10:43RuntimeError: output with shape [101, 336, 588] doesn't match the broadcast shape [101, 101, 336, 588]
- Issue#33yoomimi2025-09-09 07:27Inference using my own query points
- Issue#31okj-okj2025-09-03 15:55Track all circa 72 frames of running.mp4 instead of 4 frames
- Issue comment#21JayKarhade2025-09-01 18:31Query points and tracks2d_pred not aligned?
- Issue#29GuoAnn2025-09-01 10:04module 'utils3d.torch' has no attribute 'depth_edge'
- Issue#28sunshineinsandiego2025-08-28 20:18Frame by frame pixelwise tracking
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 458 stars here means stars gained during the window, not the repo's star count.