Research map / 3D vision / NeRF and radiance fields
DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering
Ruizhi Shao, Hongwen Zhang, He Zhang, Mingjia Chen, Yan-Pei Cao, Tao Yu, Yebin Liu
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 the shared Double MLP to associate the surface and radiance fields (ablation) | DoubleField · Twindom | PSNR: 22.01 -> 22.95 | Improved |
| Add the shared Double MLP to associate the surface and radiance fields (ablation) | DoubleField · THuman2.0 | PSNR: 23.42 -> 24.23 | Improved |
| Use the view-to-view transformer instead of average pooling for multi-view fusion (ablation) | DoubleField · Twindom | PSNR: 22.53 -> 22.95 | Improved |
| Use the view-to-view transformer instead of average pooling for multi-view fusion (ablation) | DoubleField · THuman2.0 | PSNR: 23.89 -> 24.23 | Improved |
| Add colored encoding of high-resolution RGB inputs (ablation) | DoubleField · Twindom | PSNR: 22.89 -> 22.95 | No clear effect |
| Add colored encoding of high-resolution RGB inputs (ablation) | DoubleField · THuman2.0 | PSNR: 24.11 -> 24.23 | Improved |
| Use high-resolution pixels during person-specific finetuning (ablation) | DoubleField · Twindom | PSNR: 23.28 -> 23.56 | Improved |
| Use high-resolution pixels during person-specific finetuning (ablation) | DoubleField · THuman2.0 | PSNR: 24.97 -> 25.10 | Improved |
| Finetune the proposed method for 4,000 iterations | DoubleField · Twindom | Chamfer: 0.737 -> 0.711 | Improved |
| Finetune the proposed method for 4,000 iterations | DoubleField · Twindom | PSNR: 22.95 -> 23.56 | Improved |
| Finetune the proposed method for 4,000 iterations | DoubleField · THuman2.0 | Chamfer: 0.696 -> 0.662 | Improved |
Closest papers by meaning
- Direct Voxel Grid Optimization: Super-Fast Convergence for Radiance Fields Reconstruction (CVPR 2022 · similarity 0.89)
- Light Field Neural Rendering (CVPR 2022 · similarity 0.88)
- Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting (CVPR 2023 · similarity 0.88)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.88)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.88)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.86)
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.
