Research map / 3D vision / 3D generation
From One to More: Contextual Part Latents for 3D Generation
Shaocong Dong, Lihe Ding, Xiao Chen, Yaokun Li, Yuxin Wang, Yucheng Wang, Qi Wang, Jaehyeok Kim, Chenjian Gao, Zhanpeng Huang, Zibin Wang, Tianfan Xue and 1 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use part-based latents instead of a single holistic latent (vs best baseline Rodin) | CoPart · Part-aware prompts | CLIP (I-T): 0.1571 -> 0.1768 | Improved |
| part-based latents vs holistic Trellis on whole-object prompts | CoPart · Whole-aware prompts | CLIP (N-T): 0.2071 -> 0.2010 | No clear effect |
| part-based generation vs Rodin in human preference | CoPart · User study, part-aware | preference (%): 25.5% -> 60.8% | Improved |
| part-based generation vs Rodin in human preference | CoPart · User study, whole-aware | preference (%): 33.3% -> 54.9% | Improved |
| add global guidance branch (ablation) | CoPart · qualitative ablation | part coherence | Improved |
| provide both part images and geometry to the refinement enhancer (ablation) | CoPart · qualitative ablation | part shape accuracy | Improved |
| generate a whole object as multiple parts instead of one latent | CoPart · Inference time | time: 12s -> 65s | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Unique3D — Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image (NeurIPS 2024) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models (CVPR 2025 · similarity 0.93)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.91)
- LT3SD: Latent Trees for 3D Scene Diffusion (CVPR 2025 · similarity 0.90)
- AutoPartGen: Autoregressive 3D Part Generation and Discovery (NeurIPS 2025 · similarity 0.89)
- SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation (CVPR 2025 · similarity 0.89)
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale (NeurIPS 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
