SOTAVerified

Reference-based Super-Resolution

Reference-based Super-Resolution aims to recover high-resolution images by utilizing external reference images containing similar content to generate rich textures.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 26 papers

TitleStatusHype
Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed ObservationsCode2
Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion ModelCode2
Reference-based Image and Video Super-Resolution via C2-MatchingCode2
MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby ReferencesCode1
A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-ResolutionCode1
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-ResolutionCode1
Reference-based Image Super-Resolution with Deformable Attention TransformerCode1
Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed ObservationsCode1
Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-ResolutionCode1
Dual-Camera Super-Resolution with Aligned Attention ModulesCode1
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.