特征点 Do you need robust and fast local feature extraction? You are in the right place!
Jupyter Notebook · active 2024-04-30 → 2026-08-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 834 days from 2024-04-30 to 2026-08-11. Pushes: 28 total, peak 4 in a day. Pull requests: 17 total, peak 3 in a day. Issues: 135 total, peak 5 in a day. Comments: 278 total, peak 12 in a day. Stars: 1,378 total, peak 94 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 |
|---|---|---|---|---|
| guipotje | 123 | 26 | 3 | 79 |
| noahzn | 27 | 0 | 0 | 15 |
| zw-92 | 19 | 0 | 0 | 16 |
| Asherchi | 14 | 0 | 0 | 10 |
| acai66 | 11 | 0 | 1 | 10 |
| the-cat-crying | 10 | 0 | 0 | 8 |
| noahzhy | 9 | 0 | 0 | 8 |
| IamShubhamGupto | 8 | 0 | 1 | 7 |
| longzeyilang | 7 | 0 | 0 | 5 |
| Parskatt | 7 | 0 | 1 | 4 |
| felipecadar | 6 | 1 | 0 | 5 |
| Xiaole-An | 6 | 0 | 0 | 4 |
| AI-Passionner | 6 | 0 | 0 | 3 |
| m15kh | 6 | 0 | 0 | 2 |
| Odin-byte | 5 | 0 | 0 | 4 |
| ZhouShunlong | 5 | 0 | 0 | 2 |
| hbl843449791 | 5 | 0 | 0 | 1 |
| schwert26 | 5 | 0 | 0 | 3 |
| MingYangGeng | 5 | 0 | 0 | 0 |
| cw314 | 5 | 0 | 0 | 3 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#118wangjunmars-bit2026-02-09 14:31Overlap between the MegaDepth data used for training and the MegaDepth1500 data used for evaluation
- Issue comment#94hhl1342026-01-22 12:14Problem when training xfeat+lightglue
- Issue#118kengomitsui2026-01-19 02:09Overlap between the MegaDepth data used for training and the MegaDepth1500 data used for evaluation
- Issue comment#118kengomitsui2026-01-13 23:59Overlap between the MegaDepth data used for training and the MegaDepth1500 data used for evaluation
- Issue comment#76OUCmeenoi2025-12-11 07:16根据论文写配置
- Issue comment#74jvbshsai2025-11-18 09:53Question about the MegaDepth dataset for training.
- Issue comment#113jvbshsai2025-11-18 09:51Clarification on MegaDepth Dataset Preparation & Broken Link
- Issue comment#4813034638222025-10-16 03:06training
- Issue comment#56ZHjiuang2025-10-16 02:27XFeat + GIM
- Issue#117octaAIteam2025-10-01 14:00Batch inference not faster than single inference
- Issue comment#9413034638222025-09-29 09:44Problem when training xfeat+lightglue
- Issue comment#9413034638222025-09-28 08:07Problem when training xfeat+lightglue
- Issue#114IkariKlein2025-08-19 08:53About InterpolateSparse2d
- Issue#113skbhat2025-08-14 05:32Clarification on MegaDepth Dataset Preparation & Broken Link
- Issue comment#103dinglei07192025-08-09 06:14Megadepth dataset and training convergence
- Issue#112jirongli2025-08-06 05:12Question about the smaller model
- Pull request#109Raghav-B2025-07-10 07:27
- Issue comment#34July09282025-07-09 02:26XFeat + LightGlue
- Issue comment#94July09282025-07-07 07:55Problem when training xfeat+lightglue
- Issue comment#102sr-feng2025-07-03 08:17how to convert lightglue to RKNN format, thank you
- Issue#106HumanDr2025-06-23 15:25an error in xfeat+lg_torch_hub.ipynb
- Issue comment#61cuixing1582025-05-26 08:34Can xfeat be reproduced by MATLAB?
- Issue#104noahzhy2025-05-12 15:10Question about input first two layers, mean + InstanceNorm2d
- Issue comment#57Odin-byte2025-05-12 14:02Eval-MegaDepth-1500
- Issue comment#94ZhouShunlong2025-05-12 07:38Problem when training xfeat+lightglue
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,378 stars here means stars gained during the window, not the repo's star count.