no code implementations • 22 May 2024 • Zhiping Yu, Chenyang Liu, Liqin Liu, Zhenwei Shi, Zhengxia Zou
To achieve unbounded and arbitrary-sized image generation, we design a novel noise sampling strategy for denoising diffusion models by analyzing the generation conditions and initial noise.
no code implementations • 15 Jan 2022 • Hao Chen, Yifan Zao, Liqin Liu, Song Chen, Zhenwei Shi
Here, we propose a semantic decoupled representation learning for RS image CD.