Research map / 3D vision / Face and shape
Learning a Neural 3D Texture Space From 2D Exemplars
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 transformed multi-scale noise as the MLP input, rather than exposing absolute position (ablation) | texture synthesis model · All textures | success: 8.23 -> 8.82 | Helped |
| Add learned transforms for the input noise fields (ablation) | texture synthesis model · All textures | success: 8.54 -> 8.82 | Helped |
| Add learned transforms for the input noise fields (ablation) | texture synthesis model · Wood | success: 5.40 -> 5.48 | Helped |
| Add learned transforms for the input noise fields (ablation) | texture synthesis model · Grass | success: 21.7 -> 22.1 | Helped |
| Add learned transforms for the input noise fields (ablation) | texture synthesis model · Marble | success: 9.3 -> 9.6 | Helped |
| Expose absolute position and omit transforms (ablation) | texture synthesis model · All textures | diversity: 93.4 -> 99.7 | Hurt |
| Replace pointwise neural sampling with a convolutional decoder | texture synthesis model · 3D, 128 voxels | time: 1.50\,ms -> 551.59\,ms | Hurt |
| Replace pointwise neural sampling with a convolutional decoder | texture synthesis model · 3D, 128 voxels | memory: 16\,M -> 646\,M | Hurt |
| Add an explicit diversity objective to the CNN | cnn · All textures | diversity: 0.5 -> 48.2 | Helped |
| Add explicit absolute position input (ablation) | stochastic texture sampler · All textures | diversity | Hurt |
Closest papers by meaning
- Single Mesh Diffusion Models with Field Latents for Texture Generation (CVPR 2024 · similarity 0.88)
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape (ICLR 2024 · similarity 0.88)
- TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features (CVPR 2025 · similarity 0.87)
- GenesisTex: Adapting Image Denoising Diffusion to Texture Space (CVPR 2024 · similarity 0.87)
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR 2024 · similarity 0.87)
- TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion (CVPR 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.