[CVPR 2025] VGGT: Visual Geometry Grounded Transformer
Python · active 2025-03-23 → 2026-08-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 503 days from 2025-03-23 to 2026-08-07. Pushes: 100 total, peak 19 in a day. Pull requests: 29 total, peak 3 in a day. Issues: 284 total, peak 12 in a day. Comments: 595 total, peak 17 in a day. Stars: 4,573 total, peak 121 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 |
|---|---|---|---|---|
| jytime | 333 | 100 | 8 | 193 |
| davnords | 17 | 0 | 1 | 13 |
| missTL | 10 | 0 | 0 | 7 |
| myc634 | 10 | 0 | 0 | 9 |
| zhangshuoneu | 9 | 0 | 0 | 7 |
| lifuguan | 8 | 0 | 0 | 8 |
| meta-cla[bot] | 8 | 0 | 1 | 7 |
| m43 | 7 | 0 | 0 | 5 |
| Shexiaox | 7 | 0 | 0 | 5 |
| Chinafsh | 6 | 0 | 0 | 3 |
| kevinchiu19 | 6 | 0 | 0 | 4 |
| twtynije | 6 | 0 | 0 | 2 |
| rwn17 | 6 | 0 | 0 | 5 |
| XLR-man | 5 | 0 | 0 | 3 |
| LanesraL | 5 | 0 | 0 | 5 |
| bidbest | 5 | 0 | 0 | 5 |
| kk6398 | 5 | 0 | 0 | 3 |
| seoyoung1215 | 5 | 0 | 0 | 3 |
| alsun-oven | 5 | 0 | 0 | 1 |
| barwojcik | 5 | 0 | 2 | 2 |
Recent activity
Latest issues, pull requests and releases
- Pull request#478hxh51592026-05-31 01:46
- Issue comment#417jashshah9992026-05-10 03:33Scale Issues in Model Normalised Space
- Issue comment#407jashshah9992026-05-10 03:32Applicability of VGGT for Long Sequence Images
- Issue#475Tony-Hou2026-05-02 04:31Using panoramic images to train the VGGT model, the predicted depth map has all values being a constant distribution with very low variance.
- Issue comment#473meta-cla[bot]2026-04-15 23:25[Enable inference on longer sequence without hurting performance] In…
- Issue#472xiazhenyu5552026-04-03 03:26The sequence of images will be divided into two scenes
- Issue comment#73ArchHazel2026-03-12 02:24Gradio Demo error
- Issue#464zhouxinxiang662026-03-06 03:31Why do the top and bottom boundaries of the inferred depth map seem to have some issues?
- Pull request#463dependabot[bot]2026-03-03 21:50
- Pull request#463dependabot[bot]2026-03-03 21:50
- Issue comment#377KKjiaming2026-02-28 19:58Multi-GPU parallel computing
- Issue comment#317lziiid2026-02-17 19:14How to Handle Variable-Length Batched Image Data
- Issue comment#459meta-cla[bot]2026-02-01 01:56fixed an in demo_colmap
- Issue#458RuiHuang92026-01-22 03:18Failure in Fine-tuning VGGT for Feed-forward Novel View Synthesis
- Issue comment#70ccxi10082026-01-21 11:51Is it possible to process 1000+ images on a 80G GPU?
- Issue comment#298Aawangas2026-01-20 16:22About VGGT-500M and VGGT-200M
- Issue comment#152lez-s2026-01-19 14:46How to get the Feature Confidence?
- Issue comment#374yangyuxin0305232026-01-12 03:23Is there a planning updating DINOv2 to DINOv3?
- Issue comment#199XLR-man2025-12-31 08:40How to track whole pixels?
- Issue#451HITchina2025-12-29 10:58Main File for Run
- Issue#450pbhfcycssjlmm2025-12-27 07:44[Question/Optimization] Inquiry regarding the timing of copy_data_to_device and CPU assertion
- Issue#448LeiF-u2025-12-25 08:34VGGT2Gsplat, but low PSNR and SSIM
- Issue comment#448LeiF-u2025-12-21 10:59VGGT2Gsplat, but low PSNR and SSIM
- Issue comment#439jytime2025-12-20 16:33Torch 2.7+ cuda 12.8+training error
- Issue comment#444jytime2025-12-20 16:28camera loss values
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 4,573 stars here means stars gained during the window, not the repo's star count.