Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior

2025-08-14

AI Summary

Existing reference-based super-resolution (RefSR) methods for ultra-high-definition (UHD) landmark images suffer from poor semantic alignment between low-resolution (LR) inputs and high-resolution (HR) reference images under realistic degradations, compounded by the lack of UHD-scale benchmarks with sufficient texture detail. Method: We propose TriFlowSR—the first diffusion-based framework for UHD RefSR—incorporating a generative diffusion prior, a ControlNet-enhanced architecture, and an explicit cross-resolution reference matching strategy to achieve joint semantic and textural feature alignment. Contribution/Results: We introduce Landmark-4K, the first UHD RefSR benchmark tailored to landmark scenes, comprising 4K HR references paired with realistically degraded LR counterparts. Extensive experiments demonstrate that TriFlowSR significantly improves reconstruction fidelity under real-world degradations, better exploits fine-grained structural cues from references, and consistently outperforms state-of-the-art methods across all quantitative and qualitative metrics.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Ineffective alignment between LR and reference HR images
• Limited resolution and poor quality in current RefSR datasets
• Lack of fine-grained details for high-quality restoration

Innovation

• TriFlowSR framework for explicit pattern matching
• Landmark-4K dataset for UHD landmark scenarios
• Reference Matching Strategy for real-world degradation