Multi-Frame Super-Resolution

7 papers with code • 1 benchmarks • 0 datasets

When multiple images of the same view are taken from slightly different positions, perhaps also at different times, then they collectively contain more information than any single image on its own. Multi-Frame Super-Resolution fuses these low-res inputs into a composite high-res image that can reveal some of the original detail that cannot be recovered from any low-res image alone.

( Credit: HighRes-net )

Datasets


Greatest papers with code

Wide Activation for Efficient and Accurate Image Super-Resolution

krasserm/super-resolution 27 Aug 2018

Keras-based implementation of WDSR, EDSR and SRGAN for single image super-resolution

Multi-Frame Super-Resolution

Handheld Multi-Frame Super-Resolution

kunzmi/ImageStackAlignator 8 May 2019

In this paper, we supplant the use of traditional demosaicing in single-frame and burst photography pipelines with a multiframe super-resolution algorithm that creates a complete RGB image directly from a burst of CFA raw images.

Demosaicking Multi-Frame Super-Resolution

HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery

ElementAI/HighRes-net 15 Feb 2020

Multi-frame Super-Resolution (MFSR) offers a more grounded approach to the ill-posed problem, by conditioning on multiple low-resolution views.

De-aliasing Image Registration +1

HighRes-net: Multi-Frame Super-Resolution by Recursive Fusion

ElementAI/HighRes-net ICLR 2020

Multi-frame Super-Resolution (MFSR) offers a more grounded approach to the ill-posed problem, by conditioning on multiple low-resolution views.

De-aliasing Image Registration +1

Deep Burst Super-Resolution

goutamgmb/NTIRE21_BURSTSR 26 Jan 2021

We propose a novel architecture for the burst super-resolution task.

Multi-Frame Super-Resolution Optical Flow Estimation

Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural Networks

EscVM/RAMS 6 Jul 2020

Convolutional Neural Networks (CNNs) have been consistently proved state-of-the-art results in image Super-Resolution (SR), representing an exceptional opportunity for the remote sensing field to extract further information and knowledge from captured data.

Multi-Frame Super-Resolution Representation Learning

DeepSUM: Deep neural network for Super-resolution of Unregistered Multitemporal images

diegovalsesia/deepsum 15 Jul 2019

This novel framework integrates the spatial registration task directly inside the CNN, and allows to exploit the representation learning capabilities of the network to enhance registration accuracy.

Multi-Frame Super-Resolution Representation Learning