Kaininja: Extending Native 3D Generators to the Part Level
KaiNinja extends TRELLIS.2 native 3D generation to part-level assets via a dual-volume O-Voxel representation, cutting whole-object Chamfer distance by 40%.
KaiNinja extends the TRELLIS.2 native 3D generator to produce part-level assets instead of one fused mesh, enabling downstream editing, rigging, and simulation. A dual-volume form of the O-Voxel representation solves the problem that a single volume cannot represent interfaces where two parts touch. The model needs no segmentation network, is partly trained on LLM-agent-authored part data, lowers whole-object Chamfer distance by 40%, and raises strict part F-score by 16% versus other part-generation pipelines.
- Dual-volume O-Voxel representation enables part-level native 3D generation
- First 3D generative model trained on agent-authored part data
- Cuts whole-object Chamfer distance by 40% and raises part F-score by 16%
From the original article
1 min read at huggingface.co
Native 3D generators turn one image into a single mesh. TRELLIS. 2 and its peers deliver high-fidelity non-watertight geometry with materials, but the output is one fused object, while downstream work such as editing, rigging and simulation operates on part-level assets.
By Ruihan Yu, Lian Fu, Muyao Niu · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.