Reference-Based Image Super-Resolution

Follow this topic Ask about this topic

Latest papers

10 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution
Oct 20, 2026Junyuan Deng, Xinyi Wu, Zhenyao Wu +3Image Super-Resolution Reference-Based Image Super-Resolution
Honor Device Co., Ltd. · Shenzhen University of Advanced Technology
DuSRFlow: Dual-Lens Super-Resolution via Parallax-Aware Flow Estimation and Complementary Reference Warping
Oct 10, 2026Fangpu Zhang, Huanjing Yue, Zifan Cui +3Reference-Based Image Super-Resolution Image Super-Resolution
State Key Laboratory of Smart Power Distribution Equipment and System, Tianjin University and School of Electrical and Information Engineering, Tianjin University · School of Electrical and Information Engineering, Tianjin University, Tianjin, China, 300072 · Huawei Technologies Co., Ltd.
GraftSR: Grafting Authentic Textures for Real-World Image Super-Resolution via Identical-Instance Guidance
Aug 26, 2026Qifan Yu, Haoran Bai, Zongyao He +4Reference-Based Image Super-Resolution Image Super-Resolution
Taobao & Tmall Group of Alibaba · University of Chinese Academy of Sciences
MicroZoom: Structure-Preserving Detail Synthesis at Extreme Scale
Jul 27, 2026Huy Huynh, Jingwei Ma, Brian Curless +2Image Generation Reference-Based Image Super-Resolution
University of Washington, USA
Reference-Based Face Super-Resolution Using the Spatial Transformer
Jul 13, 2026Varun Ramesh Jois, Antonella DiLillo, James StorerReference-Based Image Super-Resolution Image Super-Resolution
Brandeis University, Waltham MA 02453, USA
Cardiac MRI Through-Plane Super-Resolution Guided by Reference and Memory
Jul 8, 2026Shaoming Pan, Chenchuhui Hu, Leon Axel +13D Medical Imaging Medical Image Super-Resolution
University of Texas at Arlington · University of Texas At Arlington · New York University Grossman School of Medicine
GarmentZoom: Generating Zoomable Images from Garment Listings
Jun 28, 2026Renjie Zhao, Jingwei Ma, Huy Huynh Cao +3Reference-Based Image Super-Resolution Image Editing
University of Washington
RefGC-SR $^2$ : Reference-guided Super-Resolution and Refinement of AI Generated Content
Jun 13, 2026Jeahun Sung, Dahyeon Kye, Soo Ye Kim +1Diffusion Models for Image Restoration Reference-Based Image Super-Resolution
CMLab, Chung-Ang University · Adobe Research
Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolution
May 18, 2026Bin Luo, Runmin Dong, Zhaoyang Luo +4Diffusion Models for Image Restoration Diffusion Transformer
Tsinghua Shenzhen International Graduate School, Shenzhen, China · Sun Yat-sen University, Zhuhai, China · Tsinghua University, Beijing, China +1
InstanceRSR: Real-World Super-Resolution via Instance-Aware Representation Alignment
Mar 25, 2026Zixin Guo, Kai Zhao, Luyan ZhangReference-Based Image Super-Resolution Image Super-Resolution
Tongji University · Western Sydney University · Independent Researcher

Oct 20, 2026J/K move · Enter open · S save

WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution

Junyuan Deng, Xinyi Wu, Zhenyao Wu, Song Wang+2

Honor Device Co., Ltd. · Shenzhen University of Advanced Technology

Image Super-Resolution Reference-Based Image Super-Resolution

Open paper AskPDF arXiv

Generative-prior-based super-resolution (SR) methods leverage implicit knowledge learned from large-scale models to enhance low-resolution inputs. However, such priors are inherently stochastic and optimized for diverse generation, conflicting with the deterministic, high-fidelity reconstruction required for SR. It is also tied to the base model, costly to update, and prone to hallucinations as real-world data evolves. To address these limitations, we introduce WorldSR, a novel framework that augments SR with explicit, entity-aligned visual world knowledge. WorldSR automatically decomposes the input into semantic entities and performs entity-wise retrieval of structurally and semantically aligned images from a large-scale external corpus. For efficiency and reliability, we incorporate a memory mechanism to reuse previously retrieved results and a multi-step filtering process to refine candidate references. The selected references as world knowledge are then integrated through a novel multi-reference super-resolution model, which provides fine-grained constraints for detail synthesis and structural recovery. Experiments on real-world SR benchmarks show that WorldSR consistently improves structural fidelity and visual quality, outperforming existing generative super-resolution methods. Our results suggest that entity-level grounding in external visual world knowledge provides a simple and effective complement to model-bound generative priors.