Boosting 3D object generation through PBR materials
Normal BoostingFig. 1.Overview.Given a single image, the existing image-to-3D generative models always synthesize 3D meshes with flawed geometry and RGB textures only.Our method not only boosts existing approaches with PBR materials, empowering relighting under various lighting conditions, but also boosts the object's normal maps, capturing more intricate details and better aligning with the given image.Notably, we fine-tune Stable Diffusion to estimate the albedo map from the single-view RGB image and lift it to multi-view albedo maps for a complete albedo UV.
Authors
- Haoran Wang (ORCID: https://orcid.org/0009-0005-5823-2722)
- Y. Wang (ORCID: https://orcid.org/0009-0006-0037-7248)
- Bo Dai (ORCID: https://orcid.org/0000-0003-0777-9232)
- Li Ma (ORCID: https://orcid.org/0000-0002-6992-0089)
- Xudong Xu (ORCID: https://orcid.org/0009-0003-8858-0918)
Institutions
- Shanghai Jiao Tong University (CN)
- Fudan University (CN)
- Beijing Academy of Artificial Intelligence (CN)
- Shanghai Artificial Intelligence Laboratory (CN)
Publication Details
- Published
- 2024-12-03
- DOI
- https://doi.org/10.1145/3680528.3687676
- Citations
- 3
- Primary Topic
- Augmented Reality Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.75