[CVPR 2026] A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"
active 2025-04-20 → 2026-07-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 445 days from 2025-04-20 to 2026-07-08. Pushes: 3 total, peak 1 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 6 total, peak 1 in a day. Comments: 12 total, peak 4 in a day. Stars: 202 total, peak 27 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 |
|---|---|---|---|---|
| dimakot55 | 4 | 1 | 0 | 3 |
| N-Demir | 2 | 0 | 0 | 0 |
| jizongFox | 2 | 0 | 0 | 2 |
| MasahiroOgawa | 2 | 0 | 2 | 0 |
| GrebenkovaO | 2 | 2 | 0 | 0 |
| wurara7 | 1 | 0 | 0 | 1 |
| VISjudy | 1 | 0 | 0 | 0 |
| vrano714 | 1 | 0 | 0 | 1 |
| XiShuFan | 1 | 0 | 0 | 1 |
| yunhua-deng | 1 | 0 | 0 | 1 |
| balogistvan | 1 | 0 | 0 | 0 |
| kyuhyoung | 1 | 0 | 0 | 0 |
| TamandTat | 1 | 0 | 0 | 1 |
| venite-xjc | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#10XiShuFan2026-02-17 06:34What is the EDGS initialization method different from adopting a dense point cloud using the MVS method directly?
- Issue comment#7vrano7142025-11-06 04:49Support datasets with images with varied widths and heights
- Issue comment#10venite-xjc2025-09-27 10:14What is the EDGS initialization method different from adopting a dense point cloud using the MVS method directly?
- Issue comment#16wurara72025-09-26 10:08生成的模型没有颜色
- Issue#18N-Demir2025-07-25 19:00Support for `RADIAL` and `SIMPLE_RADIAL` cameras?
- Issue#18N-Demir2025-07-24 22:19Support for `RADIAL` and `SIMPLE_RADIAL` cameras?
- Pull request#17MasahiroOgawa2025-07-24 06:08
- Issue comment#15yunhua-deng2025-07-24 03:45`points3D.bin` - Making EDGS easier to use with other 3DGS methods
- Issue#15N-Demir2025-07-02 22:18`points3D.bin` - Making EDGS easier to use with other 3DGS methods
- Issue#14kyuhyoung2025-06-23 09:41Possibly typo.
- Pull request#13MasahiroOgawa2025-06-18 22:07
- Pull request#12MasahiroOgawa2025-06-03 05:03
- Issue comment#1dimakot552025-05-26 15:30Clarification on "5–10 seconds for COLMAP processing"
- Issue comment#9TamandTat2025-05-26 10:58Can this project run on the Windows ?
- Issue comment#11dimakot552025-05-26 09:57Questions about initialization with laser point clouds
- Issue comment#9dimakot552025-05-26 09:45Can this project run on the Windows ?
- Issue#10VISjudy2025-05-23 05:47What is the EDGS initialization method different from adopting a dense point cloud using the MVS method directly?
- Issue comment#9yunhua-deng2025-05-20 03:33Can this project run on the Windows ?
- Issue comment#2jizongFox2025-04-29 04:19vggt not available
- Issue comment#2jizongFox2025-04-25 05:51vggt not available
- Issue#6balogistvan2025-04-23 22:24Type Error problem in training.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 202 stars here means stars gained during the window, not the repo's star count.