HighRes-net: Multi-Frame Super-Resolution of satellite imagery
Pytorch implementation of HighRes-net, a neural network for multi-frame super-resolution, trained and tested on the European Space Agency’s Kelvin ...
super-resolution multi-frame-super-resolution earth-observation satellite-imagery remote-sensing proba-v highres-net computer-vision research article code paper library arxiv:2002.06460

HighRes-net is first deep learning approach to MFSR that learns its sub-tasks in an end-to-end fashion: (i) co-registration, (ii) fusion, (iii) up-sampling, and (iv) registration-at-the-loss.

By learning deep representations of multiple views, HighRes-net can super-resolve low-resolution signals and enhance Earth Observation data at scale.

HighRes-net recently topped the European Space Agency's MFSR competition on real-world satellite imagery.

Don't forget to tag @alkalait , @MichelDeudon , @shexiaogui , @rarefin , @isrugeek in your comment, otherwise they may not be notified.

Authors original post
AI for Better • ML Lead @FrontierDevelopmentLab • Super-Resolution • Founder of WellBeingInML • Mentor at @Teens-in-AI
AI enthusiastic.
Morning: Physicist Afternoon: Questioning about mind Evening: AI Enthusiast
Share this project
Similar projects
Deep Learning Based Super Resolution, Without Using a GAN
Techniques and training a deep learning model for image improvement, image restoration, inpainting and super resolution.
Deep Learning for Image Super-resolution: A Survey
This article aims to provide a comprehensive survey on recent advances of image super-resolution using deep learning approaches.
Image Super-Resolution
In this project we learn how to train a super-resolution model ESPCN on DIV2K dataset to upscale images using AI by 3x
Deep Tutorials for PyTorch
This is a series of in-depth tutorials I'm writing for implementing cool deep learning models on your own with the amazing PyTorch library.
Top collections