Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution

03/15/2022
by   Jinsu Yoo, et al.
19

Recent vision transformers along with self-attention have achieved promising results on various computer vision tasks. In particular, a pure transformer-based image restoration architecture surpasses the existing CNN-based methods using multi-task pre-training with a large number of trainable parameters. In this paper, we introduce an effective hybrid architecture for super-resolution (SR) tasks, which leverages local features from CNNs and long-range dependencies captured by transformers to further improve the SR results. Specifically, our architecture comprises of transformer and convolution branches, and we substantially elevate the performance by mutually fusing two branches to complement each representation. Furthermore, we propose a cross-scale token attention module, which allows the transformer to efficiently exploit the informative relationships among tokens across different scales. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.

READ FULL TEXT

page 8

page 10

page 12

page 15

page 16

page 17

research
03/08/2023

SANDFORMER: CNN and Transformer under Gated Fusion for Sand Dust Image Restoration

Although Convolutional Neural Networks (CNN) have made good progress in ...
research
08/17/2021

Light Field Image Super-Resolution with Transformers

Light field (LF) image super-resolution (SR) aims at reconstructing high...
research
08/24/2022

SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution

Transformer-based methods have achieved impressive image restoration per...
research
09/28/2022

Motion Transformer for Unsupervised Image Animation

Image animation aims to animate a source image by using motion learned f...
research
10/17/2022

ITSRN++: Stronger and Better Implicit Transformer Network for Continuous Screen Content Image Super-Resolution

Nowadays, online screen sharing and remote cooperation are becoming ubiq...
research
08/23/2021

Discovering Spatial Relationships by Transformers for Domain Generalization

Due to the rapid increase in the diversity of image data, the problem of...
research
03/06/2023

Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints

Learning robust local image feature matching is a fundamental low-level ...

Please sign up or login with your details

Forgot password? Click here to reset