RAMiT: Reciprocal Attention Mixing Transformer for Lightweight Image Restoration

05/19/2023
by   Haram Choi, et al.
0

Although many recent works have made advancements in the image restoration (IR) field, they often suffer from an excessive number of parameters. Another issue is that most Transformer-based IR methods focus only on either local or global features, leading to limited receptive fields or deficient parameter issues. To address these problems, we propose a lightweight IR network, Reciprocal Attention Mixing Transformer (RAMiT). It employs our proposed dimensional reciprocal attention mixing Transformer (D-RAMiT) blocks, which compute bi-dimensional (spatial and channel) self-attentions in parallel with different numbers of multi-heads. The bi-dimensional attentions help each other to complement their counterpart's drawbacks and are then mixed. Additionally, we introduce a hierarchical reciprocal attention mixing (H-RAMi) layer that compensates for pixel-level information losses and utilizes semantic information while maintaining an efficient hierarchical structure. Furthermore, we revisit and modify MobileNet V1 and V2 to attach efficient convolutions to our proposed components. The experimental results demonstrate that RAMiT achieves state-of-the-art performance on multiple lightweight IR tasks, including super-resolution, color denoising, grayscale denoising, low-light enhancement, and deraining. Codes will be available soon.

READ FULL TEXT

page 7

page 13

page 24

page 25

page 26

page 27

page 28

page 29

research
08/23/2021

SwinIR: Image Restoration Using Swin Transformer

Image restoration is a long-standing low-level vision problem that aims ...
research
04/14/2022

Residual Swin Transformer Channel Attention Network for Image Demosaicing

Image demosaicing is problem of interpolating full- resolution color ima...
research
05/23/2023

A Dive into SAM Prior in Image Restoration

The goal of image restoration (IR), a fundamental issue in computer visi...
research
09/06/2022

LRT: An Efficient Low-Light Restoration Transformer for Dark Light Field Images

Light field (LF) images with the multi-view property have many applicati...
research
10/04/2022

Accurate Image Restoration with Attention Retractable Transformer

Recently, Transformer-based image restoration networks have achieved pro...
research
05/01/2022

Reinforced Swin-Convs Transformer for Underwater Image Enhancement

Underwater Image Enhancement (UIE) technology aims to tackle the challen...
research
03/25/2023

Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables

The widespread usage of high-definition screens on edge devices stimulat...

Please sign up or login with your details

Forgot password? Click here to reset