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.

Enhancing Image Resolution of Solar Magnetograms: A Latent Diffusion Model Approach

Add code
Mar 31, 2025
Viaarxiv icon

A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only

Add code
Mar 30, 2025
Viaarxiv icon

DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution

Add code
Mar 30, 2025
Viaarxiv icon

DiffScale: Continuous Downscaling and Bias Correction of Subseasonal Wind Speed Forecasts using Diffusion Models

Add code
Mar 31, 2025
Viaarxiv icon

A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial Imagery

Add code
Mar 29, 2025
Viaarxiv icon

RELD: Regularization by Latent Diffusion Models for Image Restoration

Add code
Mar 28, 2025
Viaarxiv icon

Deterministic Medical Image Translation via High-fidelity Brownian Bridges

Add code
Mar 28, 2025
Viaarxiv icon

Evaluation of Machine-generated Biomedical Images via A Tally-based Similarity Measure

Add code
Mar 28, 2025
Viaarxiv icon

Knowledge Rectification for Camouflaged Object Detection: Unlocking Insights from Low-Quality Data

Add code
Mar 28, 2025
Viaarxiv icon

Consistency Trajectory Matching for One-Step Generative Super-Resolution

Add code
Mar 27, 2025
Viaarxiv icon