Research map / 3D vision / NeRF and radiance fields
HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs
Check 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 |
|---|---|---|---|
| Use HumanNeRF instead of IBRNet | novel-view synthesis on real testing data · Real testing data | PSNR: 30.73 -> 33.01 | Helped |
| Use HumanNeRF instead of IBRNet | novel-view synthesis on real testing data · Real testing data | SSIM: 0.9817 -> 0.9842 | Helped |
| Use HumanNeRF instead of IBRNet | novel-view synthesis on real testing data · Real testing data | LPIPS: 0.0348 -> 0.0334 | Helped |
| Use HumanNeRF instead of IBRNet | novel-view synthesis on real testing data · Real testing data | MAE: 1.154 -> 0.9307 | Helped |
| Add aggregated pixel-alignment features (ablation) | HumanNeRF · Real testing data | PSNR: 18.36 -> 33.01 | Helped |
| Add pose-embedded non-rigid deformation (ablation) | HumanNeRF · Real testing data | PSNR: 26.79 -> 33.01 | Helped |
| Add neural appearance blending (ablation) | HumanNeRF · Real testing data | PSNR: 29.69 -> 33.01 | Helped |
| Add per-subject fine-tuning (ablation) | HumanNeRF · Real testing data | PSNR: 29.51 -> 33.01 | Helped |
| Add appearance blending (ablation) | HumanNeRF without blending · Real testing data | PSNR: 25.80 -> 33.01 | Helped |
| Add radiance-field rendering (ablation) | HumanNeRF without radiance field · Real testing data | PSNR: 29.69 -> 33.01 | Helped |
| Increase input views from two to four (ablation) | HumanNeRF · Real testing data | PSNR: 22.44 -> 25.88 | Helped |
| Increase input views from four to six (ablation) | HumanNeRF · Real testing data | PSNR: 25.88 -> 32.59 | Helped |
Closest papers by meaning
- Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering (NeurIPS 2021 · similarity 0.91)
- H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion (NeurIPS 2021 · similarity 0.90)
- HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses (CVPR 2024 · similarity 0.88)
- Relightable and Animatable Neural Avatar from Sparse-View Video (CVPR 2024 · similarity 0.88)
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (AAAI 2024 · similarity 0.88)
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (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.