SOURCE-LINKED INTELLIGENCE

KaiNinja: Extending Native 3D Generators to the Part Level

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

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. A naive idea is to run a 3D segmentation network on the fused mesh that TRELLIS.2 generates, but such pipelines are slow and bounded by the accuracy of the segmentation. We want a simple way to extend an existing native 3D generator to the part level. But we face a critical problem: the O-Voxel grid stores one sheet of surface

Read original source ↗ Open in workspace

recordType

paper

region

Global