Xinjie
6a750a37be
fix(backproject): Fix mesh resimply error by adding mesh.triangulate(). ( #45 )
2025-10-01 13:11:08 +08:00
Xinjie
a34b1dacea
fix(layout): Fix layout axis order after urdf origin rotation change. ( #41 )
2025-09-26 17:23:01 +08:00
Xinjie
ee03a089b1
feat(sim): Support all simulators and opt asset storage size. ( #40 )
...
* feat(sim): Support all simulators and opt asset storage size.
2025-09-25 17:43:28 +08:00
Xinjie
cf3b919b65
feat(texture): Optimize backprojected texture quality and add texture-cli. ( #38 )
...
* feat(sim): Add auto scale in convex decomposition.
* feat(texture): Optimize back-projected texture quality.
* feat(texture): Add `texture-cli`.
2025-09-08 11:15:04 +08:00
Xinjie
e06900fe57
feat(pipe): Add layout generation by text desc pipe and release v0.1.3. ( #33 )
...
* feat(pipe): Add layout generation pipe.
* tag v0.1.3
* chore: update assets
* update
---------
Co-authored-by: xinjie.wang <xinjie.wang@gpu-4090-dev015.hogpu.cc>
2025-08-19 15:40:33 +08:00
Xinjie
c258ff8666
feat(pipe): Faster texture back projection and refine quality checkers. ( #29 )
2025-07-31 19:53:56 +08:00
Xinjie
a3924ae4a8
feat(pipe): Refine generation pipeline and add utests. ( #23 )
...
- Added intelligent quality checkers and auto-retry pipeline for `image-to-3d` and `text-to-3d`.
- Added unit tests for quality checkers.
- `text-to-3d` now supports more `text-to-image` models, pipeline success rate improved to 94%.
2025-07-11 16:51:35 +08:00
Xinjie
e8de0e44df
feat(urdf): Improve the scale restoration logic to make it more robust.( #17 )
...
Improve the scale restoration logic to make it more robust.
2025-06-27 00:39:42 +08:00
Xinjie
fec81d901a
feat(model): Update texture gen model. ( #14 )
...
Update texture gen model.
2025-06-16 02:05:17 +08:00
Xinjie
c2d4b506ae
feat(pipe): Update model auto-download set delight by default. ( #8 )
...
Update model auto-download set delight by default.
2025-06-13 03:01:29 +08:00
Xinjie
5f810f3574
chore(model): Put image_encoder to cuda to adapt to hf zero-gpu. ( #7 )
...
chore(model): Put image_encoder to cuda to adapt to hf zero-gpu.
2025-06-13 01:09:49 +08:00
Xinjie
18075659de
feat(pipeline): Add EmbodiedGen version v0.1.0. ( #2 )
...
Add EmbodiedGen version v0.1.0.
2025-06-11 22:09:22 +08:00
