Research map / 3D vision / Face and shape
SemanticHuman-HD: High Resolution Semantic disentangled 3D Human Generation
Peng Zheng, Tao Liu, Zili Yi, Rui Ma
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-aware super-resolution module (256 to 1024) (ablation) | SemanticHuman-HD · DeepFashion | FID: 13.47 -> 8.70 | Improved |
| add depth aggregation in the super-resolution module (ablation) | SemanticHuman-HD · DeepFashion 1024 | FID: 9.38 -> 8.70 | Improved |
| add upsample loss during super-resolution training (ablation) | SemanticHuman-HD · DeepFashion 1024 | FID: 13.52 -> 8.70 | Improved |
| add depth- and semantic-guided sampling to reduce sampling points | SemanticHuman-HD · Training memory, 512 res | GPU memory: 21G -> 10G (AG3D vs Ours) | Improved |
| use independent local generators per semantic part with density summed after per-part conversion | SemanticHuman-HD · DeepFashion | semantic disentanglement (qualitative) | Improved |
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.
- EVA3D — EVA3D: Compositional 3D Human Generation from 2D Image Collections (ICLR 2023) · 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
- HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion (ICLR 2024 · similarity 0.88)
- CapHuman: Capture Your Moments in Parallel Universes (CVPR 2024 · similarity 0.87)
- SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction (NeurIPS 2025 · similarity 0.87)
- HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion (CVPR 2024 · similarity 0.87)
- DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans (CVPR 2024 · similarity 0.86)
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.86)
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.
