Research map / 3D vision / Face and shape
Meshlet Priors for 3D Mesh Reconstruction
Abhishek Badki, Orazio Gallo, Jan Kautz, Pradeep Sen
Check 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 |
|---|---|---|---|
| Use learned natural meshlet priors instead of a Laplacian prior (ablation) | Local mesh patch reconstruction · 10^5 meshlets | symmetric Hausdorff distance: 0.029 -> 0.024 | Improved |
| Add global consistency to the meshlet optimization (ablation) | Full mesh reconstruction · Sparse, noisy point clouds | reconstruction quality | Improved |
| Use natural meshlet priors rather than Laplacian priors (ablation) | Full mesh reconstruction · Sparse, noisy point clouds | detail preservation and noise smoothing | Improved |
| Use Meshlets (ours) rather than Laplacian High | Mesh reconstruction · 20-object evaluation | Chamfer-L1 (mean): 0.0096 -> 0.0090 | Improved |
| Use Meshlets (ours) rather than Laplacian Low | Mesh reconstruction · 20-object evaluation | Hausdorff (mean): 0.100 -> 0.054 | Improved |
Closest papers by meaning
- Deep Optimized Priors for 3D Shape Modeling and Reconstruction (CVPR 2021 · similarity 0.89)
- Learning Self-Prior for Mesh Denoising Using Dual Graph Convolutional Networks (ECCV 2022 · similarity 0.89)
- DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery (CVPR 2024 · similarity 0.88)
- Fostering Generalization in Single-View 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors (CVPR 2021 · similarity 0.87)
- Generating 3D Faces using Convolutional Mesh Autoencoders (ECCV 2018 · similarity 0.87)
- Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction (ECCV 2020 · 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.
