Research map / Video / Video generation
Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
Yudong Jin, Sida Peng, Xuan Wang, Tao Xie, Zhen Xu, Yifan Yang, Yujun Shen, Hujun Bao, Xiaowei Zhou
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 sliding iterative denoising instead of multi-group denoising (ablation) | Diffuman4D · DNA-Rendering (3 motion sequences) | PSNR: 20.913 -> 22.363 | Improved |
| use sliding iterative denoising instead of multi-group denoising (ablation) | Diffuman4D · DNA-Rendering (3 motion sequences) | LPIPS: 0.224 -> 0.196 | Improved |
| use sliding iterative denoising instead of median filtering (ablation) | Diffuman4D · DNA-Rendering (3 motion sequences) | PSNR: 21.609 -> 22.363 | Improved |
| use sliding iterative denoising instead of median filtering (ablation) | Diffuman4D · DNA-Rendering (3 motion sequences) | LPIPS: 0.226 -> 0.196 | Improved |
| use sliding iterative denoising instead of median filtering (ablation) | Diffuman4D · DNA-Rendering (3 motion sequences) | SSIM: 0.766 -> 0.778 | Improved |
| add skeleton conditioning (ablation) | Diffuman4D · DNA-Rendering (6 complex-clothing sequences) | PSNR: 16.864 -> 22.120 | Improved |
| add skeleton conditioning (ablation) | Diffuman4D · DNA-Rendering (6 complex-clothing sequences) | SSIM: 0.608 -> 0.707 | Improved |
| add skeleton conditioning (ablation) | Diffuman4D · DNA-Rendering (6 complex-clothing sequences) | LPIPS: 0.272 -> 0.184 | Improved |
| add Plücker coordinate conditioning to skeleton conditioning (ablation) | Diffuman4D · DNA-Rendering (6 complex-clothing sequences) | PSNR: 20.753 -> 22.120 | Improved |
| add Plücker coordinate conditioning to skeleton conditioning (ablation) | Diffuman4D · DNA-Rendering (6 complex-clothing sequences) | SSIM: 0.638 -> 0.707 | Improved |
| add Plücker coordinate conditioning to skeleton conditioning (ablation) | Diffuman4D · DNA-Rendering (6 complex-clothing sequences) | LPIPS: 0.203 -> 0.184 | Improved |
| use sliding iterative denoising instead of multi-group denoising (ablation) | Diffuman4D · DNA-Rendering (3 motion sequences) | SSIM: 0.753 -> 0.778 | Improved |
Closest papers by meaning
- MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024 · similarity 0.89)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 2025 · similarity 0.89)
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.89)
- ViewFusion: Towards Multi-View Consistency via Interpolated Denoising (CVPR 2024 · similarity 0.89)
- 4Diffusion: Multi-view Video Diffusion Model for 4D Generation (NeurIPS 2024 · similarity 0.89)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 2025 · similarity 0.89)
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.
