3DDST

Generating Images with 3D Annotations Using Diffusion Models (ICLR 2024 Spotlight)

3DDST - Generating Images with 3D Annotations Using Diffusion Models (ICLR 2024 Spotlight)

Wufei Ma, Qihao Liu, Jiahao Wang, Angtian Wang, Xiaoding Yuan, Yi Zhang, Zihao Xiao, Guofeng Zhang, Beijia Lu, Ruxiao Duan, Yongrui Qi, Adam Kortylewski, Yaoyao Liu, Alan Yuille

paper :
https://arxiv.org/abs/2306.08103
project website :
https://ccvl.jhu.edu/3D-DST/

핵심 :
3D structure(shape) 정보를 담고 있는, CAD model로부터 render한 image의 edge map을
ControlNet의 visual prompts (3D geometry control)로 넣어줌으로써
Diffusion model이 특정 3D structure를 가진 image를 generate할 수 있게 함!
즉, Diffusion model generates new images where its 3D geometry can be explicitly controlled
결과적으로 Diffusion model로 data generation할 때 we can conveniently acquire GT 3D annotations for the generated 2D images

Background

Method

Overview

Prompt Generation

Result

Limitation