Research map / 3D vision / Face and shape
Neural Template: Topology-Aware Reconstruction and Disentangled Generation of 3D Meshes
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 DT-Net's input-specific topology-aware template and topology-preserving deformation instead of IM-NET | ShapeNet voxel reconstruction · ShapeNet voxels, mean | LFD: 2918.9 -> 2835.0 | Helped |
| Use DT-Net's input-specific topology-aware template and topology-preserving deformation instead of IM-NET | ShapeNet voxel reconstruction · ShapeNet voxels, mean | P2F: 0.820 -> 0.796 | Helped |
| Use DT-Net's input-specific topology-aware template and topology-preserving deformation instead of IM-NET | ShapeNet voxel reconstruction · ShapeNet voxels, mean | CD: 0.648 -> 0.573 | Helped |
| Use DT-Net instead of TMNet | ShapeNet single-view image reconstruction · ShapeNet images | LFD: 3765.5 -> 3388.3 | Helped |
| Use DT-Net instead of TMNet | ShapeNet single-view image reconstruction · ShapeNet images | P2F: 1.285 -> 1.294 | Hurt |
| Use DT-Net instead of AtlasNet | ShapeNet single-view image reconstruction · ShapeNet images | CD: 1.041 -> 1.396 | Hurt |
| Replace convex primitives with superquadrics for topology-template composition (ablation) | DT-Net · 3D mesh reconstruction | reconstruction quality | Hurt |
| Replace convex primitives with cuboids for topology-template composition (ablation) | DT-Net · 3D mesh reconstruction | reconstruction quality | Hurt |
| Replace the NODE deformation module with an invertible neural network (ablation) | DT-Net · 3D mesh reconstruction | reconstruction quality | Hurt |
Closest papers by meaning
- Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow (CVPR 2022 · similarity 0.89)
- NeuralSlice: Neural 3D Triangle Mesh Reconstruction via Slicing 4D Tetrahedral Meshes (ICML 2023 · similarity 0.89)
- Learning Deformable Tetrahedral Meshes for 3D Reconstruction (NeurIPS 2020 · similarity 0.89)
- D2IM-Net: Learning Detail Disentangled Implicit Fields From Single Images (CVPR 2021 · similarity 0.88)
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (CVPR 2024 · similarity 0.87)
- Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction (ICLR 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.