Research map / 3D vision / Face and shape
PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image
Hyeongjin Nam, Donghwan Kim, Gyeongsik Moon, Kyoung Mu Lee
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 3D part segmentation guidance to texturing (ablation) | PARTE · THuman2.1 | Part IoU: 0.461 -> 0.641 | Improved |
| add 3D part segmentation guidance to texturing (ablation) | PARTE · THuman2.1 | PSNR: 20.992 -> 22.175 | Improved |
| use image-plus-normal-map SegmentNet instead of point-cloud Human3D (ablation) | PartSegmenter · THuman2.1 | Label Acc GT: 0.881 -> 0.947 | Improved |
| add front-view part segments branch to SegmentNet (ablation) | SegmentNet · THuman2.1 | Part CD (cm): 5.087 -> 4.369 | Improved |
| use PartDiffusion instead of StableDiffusion for texturing (ablation) | PartTexturer · THuman2.1 (3D texture) | Part IoU: 0.472 -> 0.641 | Improved |
| use PartDiffusion instead of InstanceDiffusion (ablation) | PartTexturer · THuman2.1 (3D texture) | PSNR: 20.860 -> 22.175 | Improved |
| add front-view image conditioning to PartDiffusion (ablation) | PartDiffusion · THuman2.1 (3D texture) | PSNR: 21.005 -> 22.175 | Improved |
| add text prompts to PartDiffusion (ablation) | PartDiffusion · THuman2.1 (3D texture) | PSNR: 20.859 -> 22.175 | Improved |
| plug PARTE texturing into different reconstruction methods | SIFU, HumanRef, SiTH, 2K2K, TeCH · THuman2.1 | PSNR: 21.491 -> 22.412 (SIFU) | Improved |
| use PARTE instead of TeCH on geometry | 3D human reconstruction · THuman2.1 | P2S / Chamfer distance: 2.984 / 3.008 -> 2.984 / 3.008 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SIFU — SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024) · better on 2 of 2 shared results
- HumanRef — HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion (CVPR 2024) · better on 1 of 1 shared result
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
- HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation (NeurIPS 2025 · similarity 0.88)
- PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models (CVPR 2025 · similarity 0.86)
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.86)
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.85)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.85)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.85)
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.
