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.

WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning

Add code
Nov 08, 2024
Viaarxiv icon

ESC-MISR: Enhancing Spatial Correlations for Multi-Image Super-Resolution in Remote Sensing

Add code
Nov 07, 2024
Viaarxiv icon

Decoupling Fine Detail and Global Geometry for Compressed Depth Map Super-Resolution

Add code
Nov 05, 2024
Viaarxiv icon

SynthSet: Generative Diffusion Model for Semantic Segmentation in Precision Agriculture

Add code
Nov 05, 2024
Viaarxiv icon

Super-Resolution without High-Resolution Labels for Black Hole Simulations

Add code
Nov 03, 2024
Viaarxiv icon

MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D

Add code
Nov 04, 2024
Viaarxiv icon

Strongly Topology-preserving GNNs for Brain Graph Super-resolution

Add code
Nov 01, 2024
Viaarxiv icon

Constrained Diffusion Implicit Models

Add code
Nov 01, 2024
Figure 1 for Constrained Diffusion Implicit Models
Figure 2 for Constrained Diffusion Implicit Models
Figure 3 for Constrained Diffusion Implicit Models
Figure 4 for Constrained Diffusion Implicit Models
Viaarxiv icon

Blind Time-of-Flight Imaging: Sparse Deconvolution on the Continuum with Unknown Kernels

Add code
Oct 31, 2024
Viaarxiv icon

DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination

Add code
Oct 31, 2024
Viaarxiv icon