[CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.
active 2024-11-26 → 2026-06-29 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 581 days from 2024-11-26 to 2026-06-29. Pushes: 21 total, peak 5 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 50 total, peak 3 in a day. Comments: 69 total, peak 5 in a day. Stars: 164 total, peak 4 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 |
|---|---|---|---|---|
| zd11024 | 73 | 21 | 0 | 39 |
| LZ-CH | 9 | 0 | 0 | 6 |
| GoroYeh-HRI | 9 | 0 | 0 | 5 |
| Cassiel8196 | 6 | 0 | 0 | 4 |
| iris0329 | 4 | 0 | 0 | 2 |
| OliverHxh | 4 | 0 | 0 | 2 |
| hanxunyu | 4 | 0 | 0 | 2 |
| MinusOne2 | 4 | 0 | 0 | 1 |
| HuguesTHOMAS | 4 | 0 | 0 | 1 |
| Haochen-Wang409 | 2 | 0 | 0 | 1 |
| Jian-Zhang-3DV | 2 | 0 | 0 | 0 |
| aojiaosaiban | 2 | 0 | 0 | 0 |
| ZestfulJX | 1 | 0 | 0 | 0 |
| Kevin56-dot | 1 | 0 | 0 | 0 |
| dragonlong | 1 | 0 | 0 | 1 |
| ProAirVerse | 1 | 0 | 0 | 0 |
| yxchng | 1 | 0 | 0 | 0 |
| SiyuanWei | 1 | 0 | 0 | 0 |
| Jyerim | 1 | 0 | 0 | 0 |
| Vilonge | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#1FightSH2025-11-27 07:53The training time and GPU memory consumption.
- Issue#36ProAirVerse2025-10-20 06:45how did you get the 3D mask proposal for Scannet
- Issue#34ZestfulJX2025-09-22 05:23correct method for combining and extracting posed_images
- Issue comment#20YueCheong2025-08-24 13:01abnormal loss
- Issue comment#32zd110242025-07-29 05:46Training Log for Loss
- Issue comment#31zd110242025-07-22 14:01Evaluation on SQA3D doesn't match the scores in the paper
- Issue#31ruili32025-07-20 19:49Evaluation on SQA3D doesn't match the scores in the paper
- Issue#30zd110242025-06-19 08:27Question about training
- Issue#17zd110242025-06-17 02:15Is is able to train and inference with A100 GPU with 64GB memory?
- Issue comment#27GoroYeh-HRI2025-06-03 18:22Division by error issue when running `max_coverage_sampling.py`
- Issue comment#28GoroYeh-HRI2025-06-02 23:31Object ID 56 not exist in `scene0000_00.pth`
- Issue#28GoroYeh-HRI2025-06-02 23:31Object ID 56 not exist in `scene0000_00.pth`
- Issue comment#28GoroYeh-HRI2025-05-28 17:29Object ID 56 not exist in `scene0000_00.pth`
- Issue comment#28zd110242025-05-28 07:00Object ID 56 not exist in `scene0000_00.pth`
- Issue comment#27zd110242025-05-28 05:12Division by error issue when running `max_coverage_sampling.py`
- Issue comment#29GoroYeh-HRI2025-05-28 01:09Where to download ScanNet/scans/scene0707 ~ scene0806
- Issue#29GoroYeh-HRI2025-05-27 21:45Where to download ScanNet/scans/scene0707 ~ scene0806
- Issue comment#27GoroYeh-HRI2025-05-27 17:47Division by error issue when running `max_coverage_sampling.py`
- Issue#28GoroYeh-HRI2025-05-27 17:26Object ID 56 not exist in `scene0000_00.pth`
- Issue comment#25zd110242025-05-26 02:45question about eval_scanrefer
- Issue comment#27zd110242025-05-24 09:17Division by error issue when running `max_coverage_sampling.py`
- Issue#27GoroYeh-HRI2025-05-22 23:44Division by error issue when running `max_coverage_sampling.py`
- Issue#26aojiaosaiban2025-05-18 09:46question about processed data
- Issue#26aojiaosaiban2025-05-18 09:24question about processed data
- Issue#24zd110242025-05-09 15:05Question about discrete world coordinate
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 164 stars here means stars gained during the window, not the repo's star count.