“A Diffusion-Based Texturing Pipeline for Production-Grade Assets” by Lin, Smirnov and Smith
Conference:
Type(s):
Title:
- A Diffusion-Based Texturing Pipeline for Production-Grade Assets
Session/Category Title: Generative AI and Style Transfer
Presenter(s)/Author(s):
Abstract:
We introduce a pipeline for producing diverse high-quality textures for UV-unwrapped 3D assets via a Stable Diffusion Model. Our method is fast, controllable, and modular, allowing artists to work on production-grade assets and iterate quickly without making sacrifices to their standard workflows and tools.
References:
[1]
Henrik Wann Jensen. 2001. Realistic image synthesis using photon mapping. A. K. Peters, Ltd.
[2]
Yash Kant, Ziyi Wu, Michael Vasilkovsky, Guocheng Qian, Jian Ren, Riza Alp Guler, Bernard Ghanem, Sergey Tulyakov, Igor Gilitschenski, and Aliaksandr Siarohin. 2023. SPAD: Spatially Aware Multiview Diffusers. arXiv (2023).
[3]
Winnie Lin, Yilin Zhu, Demi Guo, and Ron Fedkiw. 2023. Leveraging Deepfakes to Close the Domain Gap between Real and Synthetic Images in Facial Capture Pipelines. arXiv:2204.10746 (2023).
[4]
Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D Diffusion. arXiv (2022).
[5]
Elad Richardson, Gal Metzer, Yuval Alaluf, Raja Giryes, and Daniel Cohen-Or. 2023. TEXTure: Text-Guided Texturing of 3D Shapes. In ACM SIGGRAPH 2023.
[6]
Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models.
Google Scholar
[7]
Yichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, and Xiao Yang. 2023. MVDream: Multi-view Diffusion for 3D Generation. arXiv (2023).
[8]
Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models. (2023).
[9]
Xin Yu, Peng Dai, Wenbo Li, Lan Ma, Zhengzhe Liu, and Xiaojuan Qi. 2023. Texture generation on 3d meshes with point-uv diffusion. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 4206–4216.
[10]
Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models.