A Simple Combination of Diffusion Models for Better Quality Trade-Offs in Image Denoising
This work addresses a fundamental trade-off in image denoising for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackles the problem of balancing high visual quality and low distortion in image denoising using diffusion models, achieving state-of-the-art performance with a simple hyperparameter adjustment.
Diffusion models have garnered considerable interest in computer vision, owing both to their capacity to synthesize photorealistic images and to their proven effectiveness in image reconstruction tasks. However, existing approaches fail to efficiently balance the high visual quality of diffusion models with the low distortion achieved by previous image reconstruction methods. Specifically, for the fundamental task of additive Gaussian noise removal, we first illustrate an intuitive method for leveraging pretrained diffusion models. Further, we introduce our proposed Linear Combination Diffusion Denoiser (LCDD), which unifies two complementary inference procedures - one that leverages the model's generative potential and another that ensures faithful signal recovery. By exploiting the inherent structure of the denoising samples, LCDD achieves state-of-the-art performance and offers controlled, well-behaved trade-offs through a simple scalar hyperparameter adjustment.