Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation [Siggraph Asian 2025]
active 2025-06-09 → 2026-03-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 287 days from 2025-06-09 to 2026-03-22. Pushes: 4 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 2 in a day. Comments: 14 total, peak 4 in a day. Stars: 120 total, peak 5 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 |
|---|---|---|---|---|
| ewrfcas | 11 | 4 | 0 | 7 |
| daiyixiang666 | 3 | 0 | 0 | 2 |
| Xzh-lab | 2 | 0 | 0 | 1 |
| HeathHose | 2 | 0 | 0 | 0 |
| LeeKeyu | 1 | 0 | 0 | 0 |
| jsxzs | 1 | 0 | 0 | 0 |
| FHSDHLN | 1 | 0 | 0 | 0 |
| raf-808 | 1 | 0 | 0 | 0 |
| pooyafayyazs | 1 | 0 | 0 | 0 |
| finninmunich | 1 | 0 | 0 | 0 |
| MinusOne2 | 1 | 0 | 0 | 1 |
| gangxu822 | 1 | 0 | 0 | 0 |
| Xushuolin | 1 | 0 | 0 | 0 |
| HyelinNAM | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#21finninmunich2026-02-03 09:55Do the training data need to be captioned?
- Issue#20LeeKeyu2025-12-05 03:59A question bout training dataset and epochs
- Issue#19raf-8082025-09-28 06:19请问能否用Blender生成的摄像机轨迹数据控制wan的视频生成
- Issue comment#3MinusOne22025-09-26 09:06Question about training memory
- Issue#18FHSDHLN2025-09-12 02:45May I ask about the configuration for training? I would like to know how much video memory is needed for training.
- Issue comment#17ewrfcas2025-09-04 03:35Regarding Camera Pose
- Issue#17Xushuolin2025-09-01 11:05Regarding Camera Pose
- Issue#16HyelinNAM2025-08-28 03:41T2V Human motion control
- Issue comment#15MavenDE2025-07-24 22:21Hi Uni3C team
- Issue comment#14ewrfcas2025-07-22 07:43variables
- Issue comment#15ewrfcas2025-07-22 07:31Hi Uni3C team
- Issue#15sandrumaria2025-07-19 14:29Hi Uni3C team
- Issue#14pooyafayyazs2025-07-18 04:10variables
- Issue#13HeathHose2025-07-09 02:33Question about alignment
- Issue comment#11Xzh-lab2025-07-09 01:41How to reference a video's camera controls
- Issue comment#13ewrfcas2025-07-08 15:31Question about alignment
- Issue comment#12ewrfcas2025-07-04 06:34GPU needs for generating higher resolution videos
- Issue comment#11ewrfcas2025-07-04 06:32How to reference a video's camera controls
- Issue comment#10ewrfcas2025-07-04 06:29Training Data
- Issue#13HeathHose2025-07-01 12:53Question about alignment
- Issue#11Xzh-lab2025-06-20 10:06How to reference a video's camera controls
- Issue#10jsxzs2025-06-16 23:25Training Data
- Issue#9gangxu8222025-06-16 04:11请问可以支持双人比心ai特效的生成嘛？
- Issue comment#8ewrfcas2025-06-10 12:32Generalization of the Camera Control
- Issue comment#8daiyixiang6662025-06-10 11:23Generalization of the Camera Control
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 120 stars here means stars gained during the window, not the repo's star count.