Carnegie Mellon University · Prompted 3D Part Splitting
Point2Part
A CMU model that splits a whole 3D shape into parts in one pass, so parts never overlap or leave gaps, with users choosing parts through point prompts. One model handles single image to parts, mesh to parts and part segmentation. The authors report a Chamfer distance of 0.0534 for image to parts (OmniPart: 0.0643), 0.0273 Chamfer with F1@0.05 of 0.844 and fully watertight output for mesh to parts, and 69.80 segmentation mIoU, rising to 74.84 with four prompts, all self-reported. Code on GitHub (created 29 September) with no licence file; weights not mentioned.
Open the source ↗Similar 3D & Spatial releases
- GAE
HKUST, ARC Lab (Tencent IEG), University of Hong Kong & UT Austin · Geometry-Native World Model · Week 40, 2026
- SegviGen
Beihang University, Renmin University of China, Tsinghua University, OriginArk · 3D Generation · Week 12, 2026
- PhysAg3D
Peking University, Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Huawei and Wuhan University · Interactive 3D agent · Week 45, 2026
- Idol
Speridlabs (Alejandro Cañada, Chema Garabito) · Image-to-3D splats · Week 45, 2026
- GPT-6.1 Terra Blender test
J A Z I I (@notjazii) · Blender model test · Week 45, 2026
- SKY-001
Skyfall AI · Engineering World Model · Week 44, 2026
More from Carnegie Mellon University
- FixAnything
Carnegie Mellon University · Rendering Refinement · Week 35, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.