BriefGPT.xyz
Apr, 2023
使用3D感知扩散模型实现生成新视图综合
Generative Novel View Synthesis with 3D-Aware Diffusion Models
HTML
PDF
Eric R. Chan, Koki Nagano, Matthew A. Chan, Alexander W. Bergman, Jeong Joon Park...
TL;DR
使用基于扩散的模型，结合现有的二维扩散骨架和三维特征体，进行三维感知的图像生成，同时具备自回归生成3D一致的序列能力。在合成渲染图像和实际物体上展示了最先进的效果。
Abstract
We present a
diffusion-based
model for
3d-aware
generative
novel view synthesis
from as few as a single input image. Our model samples fro
→