Research map / 3D vision / Face and shape
HoloPart: Generative 3D Part Amodal Segmentation
Yunhan Yang, Yuan-Chen Guo, Yukun Huang, Zi-Xin Zou, Zhipeng Yu, Yangguang Li, Yan-Pei Cao, Xihui Liu
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 |
|---|---|---|---|
| add context-aware attention (ablation) | HoloPart · ABO | IoU: 0.733 -> 0.764 | Improved |
| add context-aware attention (ablation) | HoloPart · PartObjaverse-Tiny | IoU: 0.553 -> 0.688 | Improved |
| add local attention (ablation) | HoloPart · PartObjaverse-Tiny | IoU: 0.618 -> 0.688 | Improved |
| use guidance scale 3.5 instead of 7.5 (ablation) | HoloPart · PartObjaverse-Tiny | IoU: 0.514 -> 0.618 | Improved |
| use guidance scale 3.5 instead of 1.5 (ablation) | HoloPart · PartObjaverse-Tiny | IoU: 0.590 -> 0.618 | Improved |
| guidance scale 5 vs 3.5 (ablation) | HoloPart · PartObjaverse-Tiny | IoU: 0.614 vs 0.618 | No clear effect |
| replace baselines with diffusion on pretrained 3D prior (HoloPart) | shape completion · ABO | Chamfer distance: 0.037 -> 0.026 vs Finetune-VAE | Improved |
| HoloPart vs best baseline on part amodal segmentation | SAMPart3D + completion · PartObjaverse-Tiny | F-Score: 0.473 -> 0.570 | Improved |
| weight learning rate 0.1x for denoiser vs context block (ablation) | HoloPart fine-tuning · qualitative | stability | Hurt |
Later papers that compared with this method
6 later accepted papers report HoloPart as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- EI-Part:Explode for Completion and Implode for Refinement (CVPR 2026 · better on 6 of 6 shared results)
- DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising (ECCV 2026 · better on 5 of 5 shared results)
- MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation (NeurIPS 2026 · better on 4 of 4 shared results)
- FullPart: Generating each 3D Part at Full Resolution (ICLR 2026 · better on 3 of 3 shared results)
- X-Part: High Fidelity And Structure Coherent Shape Decomposition And Completion (CVPR 2026 · better on 2 of 2 shared results)
- UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents (CVPR 2026 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DiffComplete — DiffComplete: Diffusion-based Generative 3D Shape Completion (NeurIPS 2023) · better on 6 of 6 shared results
- PatchComplete — PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories (NeurIPS 2022) · better on 6 of 6 shared results
- SDFusion — SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation (CVPR 2023) · better on 3 of 3 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 0.89)
- AutoPartGen: Autoregressive 3D Part Generation and Discovery (NeurIPS 2025 · similarity 0.88)
- PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding (NeurIPS 2025 · similarity 0.87)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.87)
- pix2gestalt: Amodal Segmentation by Synthesizing Wholes (CVPR 2024 · similarity 0.87)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.87)
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.
