Research map / 3D vision / 3D generation
UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation
Zexiang Liu, Yangguang Li, Youtian Lin, Xin Yu, Sida Peng, Yan-Pei Cao, Xiaojuan Qi, Xiaoshui Huang, Ding Liang, Wanli Ouyang
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 |
|---|---|---|---|
| train a diffusion model on albedo and normal maps and generate PBR materials with fixed albedo (UniDream) instead of RGB-based text-to-3D | UniDream · Text-to-3D (68 prompts) | CLIP Score: 75.7 -> 77.9 (vs MVDream) | Improved |
| use UniDream pipeline instead of MVDream | UniDream · Text-to-3D (68 prompts) | CLIP R-Precision R@1 (%): 76.8 -> 80.3 | Improved |
| use UniDream instead of MVDream in user study | UniDream · Text-to-3D user study | preference (%): 32.1 -> 50.3 | Improved |
| add normal supervision in SDS and reconstruction model | UniDream · qualitative | geometry completeness | Improved |
| optimize roughness and metallic with fixed albedo and normal, using Stable Diffusion SDS and learnable ambient light, instead of Fantasia3D | PBR stage · qualitative | light-texture disentanglement | Improved |
| train multi-view diffusion on albedo and normal instead of RGB (AN-MVM vs MVDream) | multi-view diffusion · qualitative | light/texture disentangling and normal consistency | Improved |
| mix 30% 2D LAION-Aesthetics data into multi-view training | AN-MVM · text-image semantic alignment | semantic alignment | Improved |
Closest papers by meaning
- Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation (ICLR 2024 · similarity 0.91)
- Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data (CVPR 2025 · similarity 0.90)
- HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance (ICLR 2024 · similarity 0.90)
- Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences (CVPR 2024 · similarity 0.90)
- DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors (CVPR 2024 · similarity 0.89)
- Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation (CVPR 2025 · similarity 0.89)
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.
