CasSR: Activating Image Power for Real-World Image Super-Resolution
This work addresses the problem of semantic loss and artifacts in image super-resolution for applications requiring high-quality visual restoration, representing an incremental improvement over existing diffusion-based methods.
The paper tackles the challenge of high-fidelity image super-resolution from severely degraded low-resolution images by proposing CasSR, a cascaded controllable diffusion model that generates detailed and realistic images, demonstrating efficacy and superiority through qualitative and quantitative analyses.
The objective of image super-resolution is to generate clean and high-resolution images from degraded versions. Recent advancements in diffusion modeling have led to the emergence of various image super-resolution techniques that leverage pretrained text-to-image (T2I) models. Nevertheless, due to the prevalent severe degradation in low-resolution images and the inherent characteristics of diffusion models, achieving high-fidelity image restoration remains challenging. Existing methods often exhibit issues including semantic loss, artifacts, and the introduction of spurious content not present in the original image. To tackle this challenge, we propose Cascaded diffusion for Super-Resolution, CasSR , a novel method designed to produce highly detailed and realistic images. In particular, we develop a cascaded controllable diffusion model that aims to optimize the extraction of information from low-resolution images. This model generates a preliminary reference image to facilitate initial information extraction and degradation mitigation. Furthermore, we propose a multi-attention mechanism to enhance the T2I model's capability in maximizing the restoration of the original image content. Through a comprehensive blend of qualitative and quantitative analyses, we substantiate the efficacy and superiority of our approach.