Efficient Diffusion Bridge with Initial-Value Correction Strategy for Super-Resolution

Jiati Cai, Yue Lei, Wenxin Tai, Xing He, Ting Zhong, Jia Chen, Fan Zhou

Abstract: Diffusion models have shown great potential for super-resolution by effectively mapping high-resolution images from low-resolution inputs. However, the heavy inference cost remains a significant challenge. In this work, we propose Efficient self-correcting Diffusion Bridge (EDB), a novel framework for diffusion bridge-based super-resolution. EDB introduces two key components: non-Markovian implicit sampling to improve sampling efficiency and self-correcting training to reduce estimation error. Applied to image super-resolution (SR), EDB effectively balances enhanced sampling efficiency with high image quality. Extensive quantitative and qualitative comparisons with advanced methods reveal that our method achieves competitive or even superior super-resolution performance metrics with higher sampling efficiency, highlighting its capability for accurate and efficient super-resolution of degraded images.

External IDs:dblp:conf/icmcs/CaiLTHZCZ25