YODA: You Only Diffuse Areas. An Area-Masked Diffusion Approach For Image Super-Resolution
Lists
Only you see this
Abstract
This work introduces "You Only Diffuse Areas" (YODA), a novel method for partial diffusion in Single-Image Super-Resolution (SISR). The core idea is to utilize diffusion selectively on spatial regions based on attention maps derived from the low-resolution image and the current time step in the diffusion process. This time-dependent targeting enables a more effective 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 SISR methods SR3 and SRDiff. Our experiments demonstrate new state-of-the-art performance gains in face and general SR across PSNR, SSIM, and LPIPS metrics. A notable finding is YODA's stabilization effect on training by reducing color shifts, especially when induced by small batch sizes, potentially contributing to resource-constrained scenarios. The proposed spatial and temporal adaptive diffusion mechanism opens promising research directions, including developing enhanced attention map extraction techniques and optimizing inference latency based on sparser diffusion.
BibTeX
@misc{moser2023yoda,
author = {Brian B. Moser and Stanislav Frolov and Federico Raue and Sebastian Palacio and Andreas Dengel},
title = {{YODA: You Only Diffuse Areas. An Area-Masked Diffusion Approach For Image Super-Resolution}},
year = {2023},
eprint = {2308.07977},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2308.07977},
}Loading related content...