Research map / 3D vision / Face and shape
Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement
Jiaxiang Tang, Hang Zhou, Xiaokang Chen, Tianshu Hu, Errui Ding, Jingdong Wang, Gang Zeng
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 iterative mesh refinement (fine mesh vs coarse mesh) (ablation) | NeRF2Mesh · NeRF-synthetic | Chamfer Distance (x1e-3): 7.23 -> 5.06 | Improved |
| add smoothness regularization L_smooth (ablation) | NeRF2Mesh · Mic scene | mesh size (MB): 133.0 -> 54.8 | Improved |
| add smoothness regularization L_smooth (ablation) | NeRF2Mesh · Mic scene | PSNR: 32.57 -> 31.30 | Hurt |
| add iterative mesh refinement (ablation) | NeRF2Mesh · Mic scene | mesh size (MB) and PSNR: 74.8 -> 54.8 MB; 31.06 -> 31.30 PSNR | Improved |
| add TV loss (ablation) | NeRF2Mesh · Mip-NeRF 360 | PSNR: 22.22 -> 22.36 | Improved |
| add entropy loss (ablation) | NeRF2Mesh · Mip-NeRF 360 | PSNR: 22.32 -> 22.36 | No clear effect |
| convert NeRF volume to mesh | NeRF2Mesh · NeRF-synthetic | PSNR: 30.88 -> 29.76 | Hurt |
| use surface mesh method vs NeuS on scenes with non-Lambertian surfaces | NeRF2Mesh · NeRF-synthetic Materials | Chamfer Distance (x1e-3): 4.51 vs 4.10 (NeuS) | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- MobileNeRF — MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures (CVPR 2023) · better on 2 of 5 shared results
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 2 of 3 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
- Dynamic Mesh-Aware Radiance Fields (ICCV 2023 · similarity 0.92)
- Learning Neural Duplex Radiance Fields for Real-Time View Synthesis (CVPR 2023 · similarity 0.90)
- GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement (ICLR 2025 · similarity 0.89)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.88)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.88)
- A General Implicit Framework for Fast NeRF Composition and Rendering (AAAI 2024 · similarity 0.88)
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.
