Research map / 3D vision / 3D generation
Learning Pseudo 3D Guidance for View-consistent Texturing with 2D Diffusion
Kehan Li, Yanbo Fan, Yang Wu, Zhongqian Sun, Wei Yang, Xiangyang Ji, Li Yuan, Jie Chen
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 pseudo 3D semantic guidance to multi-view texture generation (ablation) | P3G texturing pipeline · Objaverse 410 meshes | CLIP Variance: 10.20 -> 8.13 | Improved |
| add pseudo 3D semantic guidance (ablation) | P3G texturing pipeline · Objaverse 410 meshes | CLIP-IQA: 38.14 -> 46.17 | Improved |
| add pseudo 3D semantic guidance (ablation) | P3G texturing pipeline · Objaverse 410 meshes | FID: 60.1 -> 58.0 | Improved |
| add pseudo 3D semantic guidance (ablation) | P3G texturing pipeline · Objaverse 410 meshes | CLIP Score: 25.07 -> 25.53 | Improved |
| use dynamic area-maximizing view selection instead of sequential views (ablation) | P3G texturing pipeline · regular and irregular shapes | average face-view cosine over iterations | Improved |
| P3G versus TEXTure on text matching | P3G · Objaverse 410 meshes | CLIP Score: 25.66 -> 25.53 | No clear effect |
| P3G versus TEXTure in a user study | P3G · User study | Inconsistency: 23.63 -> 15.55 | Improved |
Closest papers by meaning
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.90)
- Text-Guided 3D Face Synthesis - From Generation to Editing (CVPR 2024 · similarity 0.89)
- TexTailor: Customized Text-aligned Texturing via Effective Resampling (ICLR 2025 · similarity 0.89)
- GenesisTex: Adapting Image Denoising Diffusion to Texture Space (CVPR 2024 · similarity 0.88)
- Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (CVPR 2024 · similarity 0.88)
- HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance (ICLR 2024 · similarity 0.88)
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.
