Research map / 3D vision / NeRF and radiance fields
NDF: Neural Deformable Fields for Dynamic Human Modelling
Ruiqi Zhang, Jie Chen
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 distance l to SMPL surface as third NDF dimension (sample off-surface) (ablation) | NDF · ZJU-MoCap subject 313, novel view synthesis | PSNR: 23.65 -> 29.75 | Improved |
| add distance l to SMPL surface as third NDF dimension (sample off-surface) (ablation) | NDF · ZJU-MoCap subject 313, novel pose synthesis | PSNR: 21.71 -> 23.41 | Improved |
| add pose conditioning (ablation) | NDF · ZJU-MoCap subject 313, novel view synthesis | PSNR: 21.98 -> 29.75 | Improved |
| add pose conditioning (ablation) | NDF · ZJU-MoCap subject 313, novel pose synthesis | PSNR: 20.43 -> 23.41 | Improved |
| add projection to NDF space (ablation) | NDF · ZJU-MoCap subject 313, novel view synthesis | PSNR: 29.73 -> 29.75 | No clear effect |
| add projection to NDF space (ablation) | NDF · ZJU-MoCap subject 313, novel pose synthesis | PSNR: 18.42 -> 23.41 | Improved |
| add deformation net (ablation) | NDF · ZJU-MoCap subject 313, novel view synthesis | PSNR: 29.72 -> 29.75 | No clear effect |
| add deformation net (ablation) | NDF · ZJU-MoCap subject 313, novel pose synthesis | PSNR: 23.35 -> 23.41 | Improved |
| replace default SMPL texture map with 1-piece texture map (ablation) | NDF · ZJU-MoCap subject 313, novel view synthesis | PSNR: 29.75 -> 29.93 | No clear effect |
| replace default SMPL texture map with 1-piece texture map (ablation) | NDF · ZJU-MoCap subject 313, novel pose synthesis | PSNR: 23.41 -> 23.38 | No clear effect |
| NDF versus Animatable NeRF on ZJU-MoCap novel view | NDF · ZJU-MoCap novel view synthesis | PSNR: 26.58 -> 27.17 | Improved |
| NDF versus Neural Body on ZJU-MoCap novel view | NDF · ZJU-MoCap novel view synthesis | PSNR: 27.92 -> 27.17 | Hurt |
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.
- Neural Body — Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021) · better on 6 of 8 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
- Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies (ICCV 2021 · similarity 0.91)
- Animatable Implicit Neural Representations for Creating Realistic Avatars From Videos (TPAMI 2024 · similarity 0.90)
- H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion (NeurIPS 2021 · similarity 0.89)
- Learning Neural Volumetric Representations of Dynamic Humans in Minutes (CVPR 2023 · similarity 0.88)
- A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose (NeurIPS 2021 · similarity 0.88)
- NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors (CVPR 2024 · 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.
