Research map / 3D vision / NeRF and radiance fields
H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 L_mask loss (ablation) | H-NeRF · Human3.6M | PSNR: 15.7 -> 24.4 | Helped |
| add root transformation T conditioning of NeRF appearance (ablation) | H-NeRF · RenderPeople | PSNR: 24.43 -> 28.35 | Helped |
| add L_blend loss (ablation) | H-NeRF · PeopleSnapshot | SSIM: 0.478 -> 0.86 | Helped |
| add L_blend loss (ablation) | H-NeRF · RenderPeople | Chamfer x1e-3: 0.082 -> 0.121 | Hurt |
| add imGHUM parameter fine-tuning (ablation) | H-NeRF · PeopleSnapshot | PSNR: 25.69 -> 28.12 | Helped |
| add L_geom loss (ablation) | H-NeRF · GHS3D | Chamfer x1e-3: 0.185 -> 0.113 | Helped |
| add L_geom loss (ablation) | H-NeRF · RenderPeople | IoU: 0.845 -> 0.943 | Helped |
| add L_seg loss (ablation) | H-NeRF · RenderPeople | PSNR: 26.46 -> 28.35 | Helped |
| add Gaussian noise to NeRF condition code (ablation) | H-NeRF · RenderPeople | PSNR: 26.67 -> 28.35 | Helped |
| add L_eik Eikonal regularization (ablation) | H-NeRF · GHS3D | Chamfer x1e-3: 0.104 -> 0.113 | No clear effect |
| replace NeuralBody with H-NeRF | NeuralBody · RenderPeople | Chamfer x1e-3: 0.536/0.63 -> 0.217/0.274 | Helped |
| replace NeuralBody with H-NeRF | NeuralBody · Human3.6M | PSNR: 24.86 -> 25.01 | Helped |
Closest papers by meaning
- A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose (NeurIPS 2021 · similarity 0.93)
- Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering (NeurIPS 2021 · similarity 0.92)
- A Comprehensive Benchmark for Neural Human Radiance Fields (NeurIPS 2023 · similarity 0.92)
- GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields From Multi-View Images (CVPR 2023 · similarity 0.91)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.90)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · 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.