Edify 3D: Scalable High-Quality 3D Asset Generation
NVIDIA
arXiv:2411.07135 [cs.CV], (11 Nov 2024)
@misc{nvidia2024edify3dscalablehighquality,
title={Edify 3D: Scalable High-Quality 3D Asset Generation},
author={NVIDIA and : and Maciej Bala and Yin Cui and Yifan Ding and Yunhao Ge and Zekun Hao and Jon Hasselgren and Jacob Huffman and Jingyi Jin and J. P. Lewis and Zhaoshuo Li and Chen-Hsuan Lin and Yen-Chen Lin and Tsung-Yi Lin and Ming-Yu Liu and Alice Luo and Qianli Ma and Jacob Munkberg and Stella Shi and Fangyin Wei and Donglai Xiang and Jiashu Xu and Xiaohui Zeng and Qinsheng Zhang},
year={2024},
eprint={2411.07135},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2411.07135}
}
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.
November 24, 2024 by hgpu
