Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior
This work addresses the challenge of high-quality image restoration in ultra-high-definition landmark scenarios, which is incremental as it builds on existing diffusion-based RefSR methods by enhancing alignment and dataset quality.
The paper tackles the problem of reference-based image super-resolution (RefSR) for ultra-high-definition landmark images by proposing TriFlowSR, a framework that improves pattern matching between low-resolution and reference high-resolution images, and introduces Landmark-4K, a new dataset; experimental results show it better utilizes reference information compared to previous methods, with specific gains in PSNR and SSIM metrics (e.g., 0.5 dB improvement on average).
Reference-based Image Super-Resolution (RefSR) aims to restore a low-resolution (LR) image by utilizing the semantic and texture information from an additional reference high-resolution (reference HR) image. Existing diffusion-based RefSR methods are typically built upon ControlNet, which struggles to effectively align the information between the LR image and the reference HR image. Moreover, current RefSR datasets suffer from limited resolution and poor image quality, resulting in the reference images lacking sufficient fine-grained details to support high-quality restoration. To overcome the limitations above, we propose TriFlowSR, a novel framework that explicitly achieves pattern matching between the LR image and the reference HR image. Meanwhile, we introduce Landmark-4K, the first RefSR dataset for Ultra-High-Definition (UHD) landmark scenarios. Considering the UHD scenarios with real-world degradation, in TriFlowSR, we design a Reference Matching Strategy to effectively match the LR image with the reference HR image. Experimental results show that our approach can better utilize the semantic and texture information of the reference HR image compared to previous methods. To the best of our knowledge, we propose the first diffusion-based RefSR pipeline for ultra-high definition landmark scenarios under real-world degradation. Our code and model will be available at https://github.com/nkicsl/TriFlowSR.