Variational AutoEncoder for Reference based Image Super-Resolution

06/08/2021
by   Zhi-Song Liu, et al.
0

In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE). Existing state-of-the-art methods mainly focus on single image super-resolution which cannot perform well on large upsampling factors, e.g., 8×. We propose a reference based image super-resolution, for which any arbitrary image can act as a reference for super-resolution. Even using random map or low-resolution image itself, the proposed RefVAE can transfer the knowledge from the reference to the super-resolved images. Depending upon different references, the proposed method can generate different versions of super-resolved images from a hidden super-resolution space. Besides using different datasets for some standard evaluations with PSNR and SSIM, we also took part in the NTIRE2021 SR Space challenge and have provided results of the randomness evaluation of our approach. Compared to other state-of-the-art methods, our approach achieves higher diverse scores.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 8

research
04/27/2020

Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder

Benefited from the deep learning, image Super-Resolution has been one of...
research
03/09/2023

LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution

It is widely agreed that reference-based super-resolution (RefSR) achiev...
research
11/08/2022

RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection

Reference-based image super-resolution (RefSR) is a promising SR branch ...
research
12/21/2019

Style-based Variational Autoencoder for Real-World Super-Resolution

Real-world image super-resolution is a challenging image translation pro...
research
05/20/2022

Diverse super-resolution with pretrained deep hiererarchical VAEs

Image super-resolution is a one-to-many problem, but most deep-learning ...
research
07/05/2014

A New Approach for Super resolution by Using Web Images and FFT Based Image Registration

Preserving accuracy is a challenging issue in super resolution images. I...
research
04/02/2022

Single Image Internal Distribution Measurement Using Non-Local Variational Autoencoder

Deep learning-based super-resolution methods have shown great promise, e...

Please sign up or login with your details

Forgot password? Click here to reset