Research map / 3D vision / 3D generation
TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
Yifei Zeng, Yajie Bao, Jiachen Qian, Shuang Wu, Youtian Lin, Hao Zhu, Buyu Li, Feihu Zhang, Xun Cao, Yao Yao
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 sparse latent conditioning (projected input view encoded by the attribute VAE) (ablation) | TEXTRIX DiT · Single-view texture generation (front-view reconstruction) | PSNR: 24.3984 -> 30.0985 | Improved |
| add sparse latent conditioning (ablation) | TEXTRIX DiT · Single-view texture generation (front-view reconstruction) | SSIM: 0.9052 -> 0.9421 | Improved |
| add sparse latent conditioning (ablation) | TEXTRIX DiT · Single-view texture generation (front-view reconstruction) | LPIPS: 0.0942 -> 0.0627 | Improved |
| native 3D attribute grid instead of TRELLIS DINOv2 features | texture generation · Single-view texture generation (front-view reconstruction) | PSNR: 25.5405 -> 30.0985 | Improved |
| combine TEXTRIX with MVAdapter for multi-view conditioning | MVAdapter · Multi-view texturing (novel-view) | CLIP-FID: 21.9120 -> 21.7571 | Improved |
| use TEXTRIX for part segmentation vs PartField | class-agnostic part segmentation · Objaverse (Complex) part segmentation, 100 meshes | mIoU: 51.79 -> 60.82 | Improved |
| use TEXTRIX for part segmentation vs PartField | class-agnostic part segmentation · Objaverse (Random) part segmentation, 100 meshes | mIoU: 74.63 -> 72.26 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- PartField — PartField: Learning 3D Feature Fields for Part Segmentation and Beyond (ICCV 2025) · better on 1 of 2 shared results
- Paint3D — Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (CVPR 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.87)
- PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models (CVPR 2025 · similarity 0.87)
- Structured 3D Latents for Scalable and Versatile 3D Generation (CVPR 2025 · similarity 0.87)
- LT3SD: Latent Trees for 3D Scene Diffusion (CVPR 2025 · similarity 0.86)
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape (ICLR 2024 · similarity 0.86)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (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.
