Research map / 3D vision / 3D generation
FISHuman: Fine-grained Single-image 3D Human Reconstruction via Multi-view 4D Remeshing
Hanxi Liu, Yifang Men, Zhouhui Lian
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 cross-modal attention alignment between RGB and normal streams (ablation) | FISHuman · 2K2K | PSNR: 23.14 -> 24.49 | Improved |
| add cross-modal attention alignment between RGB and normal streams (ablation) | FISHuman · 2K2K | LPIPS: 0.1015 -> 0.0858 | Improved |
| add 4D remeshing module on top of static remeshing (ablation) | FISHuman · 2K2K | PSNR: 23.87 -> 24.49 | Improved |
| add 4D remeshing module on top of static remeshing (ablation) | FISHuman · 2K2K | LPIPS: 0.0970 -> 0.0858 | Improved |
| add 3D-aware finetuning of the video generator on multi-view human renderings (ablation) | dual-stream video generator · qualitative, in-the-wild | visual 3D consistency | Improved |
| use two-stage progressive training instead of joint training of dual-stream and cross-modal alignment (ablation) | dual-stream video generator · qualitative | visual quality | Improved |
| replace static 3D remeshing with 4D remeshing (ablation) | FISHuman · qualitative | geometry quality | Improved |
| use FISHuman instead of PSHuman | single-image 3D human reconstruction · 2K2K | Chamfer Distance (cm): 1.133 -> 0.817 | Improved |
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.
- PSHuman — PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025) · better on 6 of 6 shared results
- Human3Diffusion — Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models (NeurIPS 2024) · better on 5 of 5 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
- MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement (AAAI 2025 · similarity 0.89)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.89)
- GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data (NeurIPS 2025 · similarity 0.89)
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.88)
- One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion (CVPR 2024 · similarity 0.88)
- Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses (CVPR 2024 · 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.
