Edify 3D: Scalable High-Quality 3D Asset Generation
NVIDIA: Maciej Bala, Yin Cui, Yifan Ding, Yunhao Ge, Zekun Hao, Jon, Hasselgren, Jacob Huffman, Jingyi Jin, J.P. Lewis, Zhaoshuo Li, Chen-Hsuan, Lin, Yen-Chen Lin, Tsung-Yi Lin, Ming-Yu Liu, Alice Luo, Qianli Ma, Jacob, Munkberg, Stella Shi, Fangyin Wei, Donglai Xiang, Jiashu Xu

TL;DR
Edify 3D presents a scalable diffusion-based approach for rapid high-quality 3D asset generation, producing detailed geometry, textures, and materials within minutes.
Contribution
The paper introduces a novel multi-view diffusion model that synthesizes images for efficient 3D reconstruction, enabling fast and detailed asset creation.
Findings
Generates high-quality 3D assets in under 2 minutes
Produces detailed geometry and high-resolution textures
Reconstructs shape, texture, and materials accurately
Abstract
We introduce Edify 3D, an advanced solution designed for high-quality 3D asset generation. Our method first synthesizes RGB and surface normal images of the described object at multiple viewpoints using a diffusion model. The multi-view observations are then used to reconstruct the shape, texture, and PBR materials of the object. Our method can generate high-quality 3D assets with detailed geometry, clean shape topologies, high-resolution textures, and materials within 2 minutes of runtime.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputer Graphics and Visualization Techniques
MethodsDiffusion
