1 code implementation • 17 May 2024 • HanYu Chen, Zhixiu Hao, Liying Xiao
To address the challenges, we propose Deep Data Consistency (DDC) to update the data consistency step with a deep learning model when solving inverse problems with diffusion models.
no code implementations • 14 Mar 2024 • HanYu Chen, Zhixiu Hao, Lin Guo, Liying Xiao
This study introduces a novel Cascaded Diffusion with Discrepancy Mitigation (CDDM) framework, including the low-quality image generation in latent space and the high-quality image generation in pixel space which contains data consistency and discrepancy mitigation in a one-step reconstruction process.