Research map / 3D vision / Face and shape
NSF: Neural Surface Fields for Human Modeling from Monocular Depth
Yuxuan Xue, Bharat Lal Bhatnagar, Riccardo Marin, Nikolaos Sarafianos, Yuanlu Xu, Gerard Pons-Moll, Tony Tung
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 pose-dependent NSF deformation to fusion shape (ablation) | NSF · BuFF | Chamfer distance (cm): 0.97 -> 0.69 | Improved |
| add pose-dependent NSF deformation to fusion shape (ablation) | NSF · CAPE | Chamfer distance (cm): 0.86 -> 0.65 | Improved |
| add pose-dependent NSF deformation to fusion shape (ablation) | NSF · ReSynth | IoU: 0.846 -> 0.887 | Improved |
| use neural surface features instead of volumetric features (ablation) | NSF deformation decoder · BuFF subject 00032 | Chamfer distance: 0.77 -> 0.66 | Improved |
| use neural surface features instead of triplane features (ablation) | NSF deformation decoder · BuFF subject 00032 | Chamfer distance: 0.74 -> 0.66 | Improved |
| NSF versus PINA on CAPE | NSF · CAPE | Chamfer distance (cm): 0.62 -> 0.65 | Hurt |
| fine-tune only subject features on 10 frames instead of full training on 126 frames | NSF pretrained network · BuFF subject 00114 | Chamfer distance: 0.80 -> 0.87 | No clear effect |
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.
- PINA — PINA: Learning a Personalized Implicit Neural Avatar From a Single RGB-D Video Sequence (CVPR 2022) · better on 3 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
- MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images (NeurIPS 2021 · similarity 0.90)
- MonoHuman: Animatable Human Neural Field From Monocular Video (CVPR 2023 · similarity 0.89)
- Dynamic Point Fields (ICCV 2023 · similarity 0.89)
- Relightable and Animatable Neural Avatar from Sparse-View Video (CVPR 2024 · similarity 0.87)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.87)
- HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstruction (AAAI 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.
