CoSeR: Bridging Image and Language for Cognitive Super-Resolution
This work addresses the issue of semantic accuracy in image super-resolution for applications requiring high-fidelity visual restoration, representing an incremental improvement by combining existing techniques in a novel way.
The paper tackles the problem of super-resolution models neglecting global semantic information, which can lead to missing or inaccurate details, by introducing the CoSeR framework that integrates image and language understanding to generate cognitive embeddings and uses a novel condition injection scheme, achieving state-of-the-art performance on multiple benchmarks.
Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the introduction of inaccurate textures during the recovery process. In our work, we introduce the Cognitive Super-Resolution (CoSeR) framework, empowering SR models with the capacity to comprehend low-resolution images. We achieve this by marrying image appearance and language understanding to generate a cognitive embedding, which not only activates prior information from large text-to-image diffusion models but also facilitates the generation of high-quality reference images to optimize the SR process. To further improve image fidelity, we propose a novel condition injection scheme called "All-in-Attention", consolidating all conditional information into a single module. Consequently, our method successfully restores semantically correct and photorealistic details, demonstrating state-of-the-art performance across multiple benchmarks. Code: https://github.com/VINHYU/CoSeR