Edify 3D: Scalable High-Quality 3D Asset Generation
NVIDIA, :, Bala, Maciej, Yin Cui, Yifan Ding, Yunhao Ge, Zekun Hao, Jon Hasselgren, Huffman, Jacob, Jingyi Jin, Lewis, J. P., Zhaoshuo Li, Chen-Hsuan Lin, Yen-Chen Lin, Tsung-Yi Lin, Mingyu Liu, Luo, Alice, Qianli Ma, Jacob Munkberg, Shi, Stella · arXiv (Cornell University) · 2024
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.