Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ai, Yuang, Huang, Huaibo, Wu, Tao, Fan, Qihang, He, Ran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913851977498624
author Ai, Yuang
Huang, Huaibo
Wu, Tao
Fan, Qihang
He, Ran
author_facet Ai, Yuang
Huang, Huaibo
Wu, Tao
Fan, Qihang
He, Ran
contents Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this issue with sparse or window-based attention, yet inherently limit global context modeling. Linear attention, a variant of softmax attention, demonstrates promise in global context modeling while maintaining linear complexity, offering a potential solution to the above challenge. Despite its efficiency benefits, vanilla linear attention suffers from a significant performance drop in IR, largely due to the low-rank nature of its attention map. To counter this, we propose Rank Enhanced Linear Attention (RELA), a simple yet effective method that enriches feature representations by integrating a lightweight depthwise convolution. Building upon RELA, we propose an efficient and effective image restoration Transformer, named LAformer. LAformer achieves effective global perception by integrating linear attention and channel attention, while also enhancing local fitting capabilities through a convolutional gated feed-forward network. Notably, LAformer eliminates hardware-inefficient operations such as softmax and window shifting, enabling efficient processing of high-resolution images. Extensive experiments across 7 IR tasks and 21 benchmarks demonstrate that LAformer outperforms SOTA methods and offers significant computational advantages.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16157
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention
Ai, Yuang
Huang, Huaibo
Wu, Tao
Fan, Qihang
He, Ran
Computer Vision and Pattern Recognition
Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this issue with sparse or window-based attention, yet inherently limit global context modeling. Linear attention, a variant of softmax attention, demonstrates promise in global context modeling while maintaining linear complexity, offering a potential solution to the above challenge. Despite its efficiency benefits, vanilla linear attention suffers from a significant performance drop in IR, largely due to the low-rank nature of its attention map. To counter this, we propose Rank Enhanced Linear Attention (RELA), a simple yet effective method that enriches feature representations by integrating a lightweight depthwise convolution. Building upon RELA, we propose an efficient and effective image restoration Transformer, named LAformer. LAformer achieves effective global perception by integrating linear attention and channel attention, while also enhancing local fitting capabilities through a convolutional gated feed-forward network. Notably, LAformer eliminates hardware-inefficient operations such as softmax and window shifting, enabling efficient processing of high-resolution images. Extensive experiments across 7 IR tasks and 21 benchmarks demonstrate that LAformer outperforms SOTA methods and offers significant computational advantages.
title Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.16157