Dynamic Attention-Guided Diffusion for Image Super-Resolution

Abstract

Diffusion models in image Super-Resolution (SR) treat all image regions uniformly, which risks compromising the overall image quality by potentially introducing artifacts during denoising of less-complex regions. To address this, we propose ``You Only Diffuse Areas'' (YODA), a dynamic attention-guided diffusion process for image SR. YODA selectively focuses on spatial regions defined by attention maps derived from the low-resolution images and the current denoising time step. This time-dependent targeting enables a more efficient conversion to high-resolution outputs by focusing on areas that benefit the most from the iterative refinement process, i.e., detail-rich objects. We empirically validate YODA by extending leading diffusion-based methods SR3, DiffBIR, and SRDiff. Our experiments demonstrate new state-of-the-art performances in face and general SR tasks across PSNR, SSIM, and LPIPS metrics. As a side effect, we find that YODA reduces color shift issues and stabilizes training with small batches.

Brian B. Moser and Stanislav Frolov contributed equally

References in corpus (6)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Learned Image Downscaling for Upscaling using Content Adaptive Resampler
• Diffusion Models, Image Super-Resolution And Everything: A Survey
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• DWA: Differential Wavelet Amplifier for Image Super-Resolution