Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors
This addresses the problem of generating high-resolution images that meet human perceptual standards for applications in image processing, though it appears incremental as it builds on existing diffusion models.
The paper tackles the challenge of achieving semantic consistency and perceptual naturalness in real-world super-resolution under heavy degradation and varied input complexities, proposing Hero-SR, a one-step diffusion-based framework with human perception priors, which achieves state-of-the-art performance in Real-SR.
Owing to the robust priors of diffusion models, recent approaches have shown promise in addressing real-world super-resolution (Real-SR). However, achieving semantic consistency and perceptual naturalness to meet human perception demands remains difficult, especially under conditions of heavy degradation and varied input complexities. To tackle this, we propose Hero-SR, a one-step diffusion-based SR framework explicitly designed with human perception priors. Hero-SR consists of two novel modules: the Dynamic Time-Step Module (DTSM), which adaptively selects optimal diffusion steps for flexibly meeting human perceptual standards, and the Open-World Multi-modality Supervision (OWMS), which integrates guidance from both image and text domains through CLIP to improve semantic consistency and perceptual naturalness. Through these modules, Hero-SR generates high-resolution images that not only preserve intricate details but also reflect human perceptual preferences. Extensive experiments validate that Hero-SR achieves state-of-the-art performance in Real-SR. The code will be publicly available upon paper acceptance.