Super Resolution


Super-resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.

RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution

Add code
Apr 22, 2025
Viaarxiv icon

Survey of Video Diffusion Models: Foundations, Implementations, and Applications

Add code
Apr 22, 2025
Viaarxiv icon

DSPO: Direct Semantic Preference Optimization for Real-World Image Super-Resolution

Add code
Apr 21, 2025
Viaarxiv icon

NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study

Add code
Apr 21, 2025
Viaarxiv icon

STARS: Sparse Learning Correlation Filter with Spatio-temporal Regularization and Super-resolution Reconstruction for Thermal Infrared Target Tracking

Add code
Apr 20, 2025
Viaarxiv icon

NTIRE 2025 Challenge on Image Super-Resolution ($\times$4): Methods and Results

Add code
Apr 20, 2025
Viaarxiv icon

SupResDiffGAN a new approach for the Super-Resolution task

Add code
Apr 18, 2025
Viaarxiv icon

Equilibrium Conserving Neural Operators for Super-Resolution Learning

Add code
Apr 18, 2025
Viaarxiv icon

AnyTSR: Any-Scale Thermal Super-Resolution for UAV

Add code
Apr 18, 2025
Viaarxiv icon

Event-Enhanced Blurry Video Super-Resolution

Add code
Apr 18, 2025
Viaarxiv icon