DiffusionGS: Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation
Yuanhao Cai1, He Zhang2, Kai Zhang2,
Yixun Liang3, Mengwei Ren2, Fujun Luan2, Qing Liu2,
Soo Ye Kim2, Jianming Zhang2, Zhifei Zhang2, Yuqian Zhou2,
Zhe Lin2, Alan Yuille1
1 Johns Hopkins University 2 Adobe Research 3 HKUST
A one-stage 3DGS-based diffusion generates objects and scenes from a single view in ~6 seconds.
