Research map / 3D vision / Face and shape
Neural 3D Mesh Renderer
Read the paperCheck 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 mesh-based reconstruction instead of voxel-based reconstruction | Single-image 3D reconstruction · ShapeNetCore mean | voxel IoU: 0.5736 -> 0.6016 | Helped |
| use mesh-based reconstruction instead of voxel-based reconstruction | Single-image 3D reconstruction · ShapeNetCore airplane, bench, dresser, chair, display, loudspeaker, rifle, sofa, telephone, vessel | voxel IoU | Helped |
| use mesh-based reconstruction instead of voxel-based reconstruction | Single-image 3D reconstruction · ShapeNetCore car, lamp, table | voxel IoU | Hurt |
| add the smoothness regularizer (ablation) | Mesh-based single-image 3D reconstruction · ShapeNetCore | surface smoothness | Helped |
| add the smoothness regularizer (ablation) | Mesh-based single-image 3D reconstruction · ShapeNetCore | voxel IoU | Hurt |
| use the approximate-gradient Neural Renderer to enable gradient-based mesh editing with 2D image losses | Neural Renderer · 2D-to-3D style transfer | style transfer quality | Helped |
| use the approximate-gradient Neural Renderer to optimize mesh vertices and textures | Neural Renderer · 3D DeepDream | feature visualization | Helped |
Closest papers by meaning
- MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model (NeurIPS 2024 · similarity 0.88)
- Multi-View Mesh Reconstruction With Neural Deferred Shading (CVPR 2022 · similarity 0.88)
- Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer (NeurIPS 2019 · similarity 0.88)
- QUADify: Extracting Meshes with Pixel-level Details and Materials from Images (CVPR 2024 · similarity 0.86)
- MeshXL: Neural Coordinate Field for Generative 3D Foundation Models (NeurIPS 2024 · similarity 0.85)
- What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs (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.