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

• URL: http://arxiv.org/abs/2505.16157v1
• Date: Thu, 22 May 2025 02:57:23 GMT
• Title: Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention
• Authors: Yuang Ai, Huaibo Huang, Tao Wu, Qihang Fan, Ran He,
• Abstract summary: Linear attention, a variant of softmax attention, demonstrates promise in global context modeling.<n>We propose Rank Enhanced Linear Attention (RELA), a simple yet effective method that enriches feature representations by integrating a lightweight depthwise convolution.<n>Building upon RELA, we propose an efficient and effective image restoration Transformer, named LAformer.
• Score: 54.42902794496325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Global Modeling Matters: A Fast, Lightweight and Effective Baseline for Efficient Image Restoration [9.2933763571933]
  Pyramid Wavelet-Fourier Network (PW-FNet) is an efficient restoration baseline for image restoration.<n>PW-FNet features multi-input multi-output structure to achieve multi-scale and multi-frequency bands decomposition.<n>Experiments on tasks such as image deraining, raindrop removal, image super-resolution, motion deblurring, image dehazing and underwater/low-light enhancement demonstrate that PW-FNet not only surpasses state-of-the-art methods in restoration quality but also achieves superior efficiency.
  arXiv  Detail & Related papers  (2025-07-18T05:15:04Z)
• Joint multi-dimensional dynamic attention and transformer for general image restoration [14.987034136856463]
  outdoor images often suffer from severe degradation due to rain, haze, and noise. Current image restoration methods struggle to handle complex degradation while maintaining efficiency. This paper introduces a novel image restoration architecture that combines multi-dimensional dynamic attention and self-attention.
  arXiv  Detail & Related papers  (2024-11-12T15:58:09Z)
• Breaking the Low-Rank Dilemma of Linear Attention [61.55583836370135]
  Linear attention provides a far more efficient solution by reducing the complexity to linear levels.<n>Our experiments indicate that this performance drop is due to the low-rank nature of linear attention's feature map.<n>We introduce Rank-Augmented Linear Attention (RALA), which rivals the performance of Softmax attention while maintaining linear complexity and high efficiency.
  arXiv  Detail & Related papers  (2024-11-12T08:30:59Z)
• LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration [62.3751291442432]
  We propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. Experiments demonstrate that LoRA-IR achieves SOTA performance across 14 IR tasks and 29 benchmarks, while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2024-10-20T13:00:24Z)
• Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution [80.85121353651554]
  We introduce kernel-wise differential operations within the convolutional kernel and develop several learnable directional gradient convolutions. These convolutions are integrated in parallel with a novel linear weighting mechanism to form an Adaptive Directional Gradient Convolution (DGConv) We further devise an Adaptive Information Interaction Block (AIIBlock) to adeptly balance the enhancement of texture and contrast while meticulously investigating the interdependencies, culminating in the creation of a DGPNet for Real-SR through simple stacking.
  arXiv  Detail & Related papers  (2024-05-11T14:21:40Z)
• FLatten Transformer: Vision Transformer using Focused Linear Attention [80.61335173752146]
  Linear attention offers a much more efficient alternative with its linear complexity. Current linear attention approaches either suffer from significant performance degradation or introduce additional computation overhead. We propose a novel Focused Linear Attention module to achieve both high efficiency and expressiveness.
  arXiv  Detail & Related papers  (2023-08-01T10:37:12Z)
• Cross-Spatial Pixel Integration and Cross-Stage Feature Fusion Based Transformer Network for Remote Sensing Image Super-Resolution [13.894645293832044]
  Transformer-based models have shown competitive performance in remote sensing image super-resolution (RSISR) We propose a novel transformer architecture called Cross-Spatial Pixel Integration and Cross-Stage Feature Fusion Based Transformer Network (SPIFFNet) for RSISR. Our proposed model effectively enhances global cognition and understanding of the entire image, facilitating efficient integration of features cross-stages.
  arXiv  Detail & Related papers  (2023-07-06T13:19:06Z)
• RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution [57.98314517861539]
  Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images. In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network.
  arXiv  Detail & Related papers  (2023-06-30T12:14:13Z)
• Large-scale Global Low-rank Optimization for Computational Compressed Imaging [8.594666859332124]
  We present the global low-rank (GLR) optimization technique, realizing highly-efficient large-scale reconstruction with global self-similarity. Inspired by the self-attention mechanism in deep learning, GLR extracts image patches by feature detection instead of conventional uniform selection. We experimentally demonstrate GLR's effectiveness on temporal, frequency, and spectral dimensions.
  arXiv  Detail & Related papers  (2023-01-08T14:12:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.