Research map / 3D vision / Face and shape
MeshFeat: Multi-Resolution Features for Neural Fields on Meshes
Mihir Mahajan, Florian Hofherr, Daniel Cremers
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 Laplacian feature regularization (ablation) | MeshFeat · Texture reconstruction, human | PSNR: 31.25 -> 32.51 | Improved |
| add Laplacian feature regularization (ablation) | MeshFeat · Texture reconstruction, cat | PSNR: 33.27 -> 34.23 | Improved |
| increase feature dimension from 4 to 10 (ablation) | MeshFeat · Texture reconstruction, cat (coarse mesh) | PSNR: 34.23 -> 34.65 | Improved |
| increase feature dimension from 4 to 10 (ablation) | MeshFeat · Texture reconstruction, human (fine mesh) | PSNR: 32.51 -> 32.46 | No clear effect |
| use multi-resolution features instead of single resolution (ablation) | MeshFeat · Texture reconstruction validation PSNR | PSNR | Improved |
| include the original resolution (r=1) as finest level (ablation) | MeshFeat · Texture reconstruction, human | PSNR: 31.51 -> 32.51 | Improved |
| use a very low feature dimension (d=1 vs d=4) (ablation) | MeshFeat · Texture reconstruction, human | PSNR: 32.51 -> 29.30 | Hurt |
| shrink MLP to one hidden layer or width 16 (ablation) | MeshFeat · Texture reconstruction, human | PSNR: 32.51 -> 32.39 | Hurt |
| use parametric multi-resolution mesh features instead of frequency encodings | MeshFeat vs INF · Texture reconstruction, human | inference speedup: 3.06x -> 13.49x | Improved |
Closest papers by meaning
- Mesh2Tex: Generating Mesh Textures from Image Queries (ICCV 2023 · similarity 0.89)
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (CVPR 2024 · similarity 0.86)
- Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing (NeurIPS 2025 · similarity 0.86)
- LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering (CVPR 2024 · similarity 0.86)
- Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction (ICLR 2024 · similarity 0.86)
- PoNQ: a Neural QEM-based Mesh Representation (CVPR 2024 · similarity 0.85)
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.
