Lee_Reference-based_Super-Resolution_via_Image-based_Retrieval-Augmented_Generation_Diffusion@ICCV2025@CVF

Total: 1

#1 Reference-based Super-Resolution via Image-based Retrieval-Augmented Generation Diffusion [PDF4] [Copy] [Kimi1] [REL]

Authors: Byeonghun Lee, Hyunmin Cho, Hong Gyu Choi, Soo Min Kang, Iljun Ahn, Kyong Hwan Jin

Most existing diffusion models have primarily utilized reference images for image-to-image translation rather than for super-resolution (SR). In SR-specific tasks, diffusion methods rely solely on low-resolution (LR) inputs, limiting their ability to leverage reference information. Prior reference-based diffusion SR methods have shown that incorporating appropriate references can significantly enhance reconstruction quality; however, identifying suitable references in real-world scenarios remains a critical challenge. Recently, Retrieval-Augmented Generation (RAG) has emerged as an effective framework that integrates retrieval-based and generation-based information from databases to enhance the accuracy and relevance of responses. Inspired by RAG, we propose an image-based RAG framework (iRAG) for realistic super-resolution, which employs a trainable hashing function to retrieve either real-world or generated references given an LR query. Retrieved patches are passed to a restoration module that generates high-fidelity super-resolved features, and a hallucination filtering mechanism is used to refine generated references from pre-trained diffusion models. Experimental results demonstrate that our approach not only resolves practical difficulties in reference selection but also delivers superior performance over existing diffusion and non-diffusion RefSR methods. Code is available at https://github.com/ByeonghunLee12/iRAG.

Subject: ICCV.2025 - Poster