Dual-volume representation gives 3D generators part-level output
KaiNinja uses dual-volume representation to extend TRELLIS.2-class generators to part level, with authors claiming a 40% Chamfer distance drop.
ImportanceLocalEvidenceE2 unreplicated
Readers can now have TRELLIS.2-class native 3D generators produce part-level results directly without a segmenter, with the authors claiming a 40% drop in whole-object Chamfer distance versus part-generation pipelines of a different paradigm and a 16% rise in strict part F-score.
Previously, voxel grids could not express part contact surfaces, so part-level generation relied on segmenters or a different-paradigm pipeline, at the cost of limited accuracy and part consistency.
The result was measured by Ruihan Yu and 11 others, using a dual-volume representation to address that contact-surface expression problem, with training data including part assets generated by an LLM agent.
Boundary: the results have not been peer-reviewed and have no independent reproduction; the preprint was released on September 14, arXiv ID 2609.15659.