notesum.ai

Published at November 19

CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis

cs.CV

cs.AI

Released Date: November 19, 2024

Authors: Yifan Xie¹, Jingge Wang², Tao Feng², Fei Ma³, Yang Li²

Aff.: ¹School of Software Engineering, Xi'an Jiaotong University, Xi'an, China; ²Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China; ³Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China

Arxiv: http://arxiv.org/abs/2411.12198v1

Method	FID $\downarrow$	CLIP-score $\uparrow$	CLIP-image $\uparrow$
ControlNet	87.32	30.78	87.09
Uni-ControlNet	92.74	30.57	86.46
Ours	71.73	31.96	88.70