Papers: arxiv:2305.07015

Exploiting Diffusion Prior for Real-World Image Super-Resolution

Zongsheng Yue ,
Shangchen Zhou ,
Kelvin C. K. Chan ,
Chen Change Loy
·published on May 11


We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model, thereby preserving the generative prior and minimizing training cost. To remedy the loss of fidelity caused by the inherent stochasticity of diffusion models, we introduce a controllable feature wrapping module that allows users to balance quality and fidelity by simply adjusting a scalar value during the inference process. Moreover, we develop a progressive aggregation sampling strategy to overcome the fixed-size constraints of pre-trained diffusion models, enabling adaptation to resolutions of any size. A comprehensive evaluation of our method using both synthetic and real-world benchmarks demonstrates its superiority over current state-of-the-art approaches.


Sign up or log in to comment

Models citing this paper 1