A Low-Resolution Image is Worth 1x1 Words: Enabling Fine Image Super-Resolution with Transformers and TaylorShift

• URL: http://arxiv.org/abs/2411.10231v1
• Date: Fri, 15 Nov 2024 14:43:58 GMT
• Title: A Low-Resolution Image is Worth 1x1 Words: Enabling Fine Image Super-Resolution with Transformers and TaylorShift
• Authors: Sanath Budakegowdanadoddi Nagaraju, Brian Bernhard Moser, Tobias Christian Nauen, Stanislav Frolov, Federico Raue, Andreas Dengel,
• Abstract summary: We propose TaylorIR to address limitations by utilizing a patch size of 1x1, enabling pixel-level processing in any transformer-based SR model. Experimental results demonstrate that our approach achieves new state-of-the-art SR performance while reducing memory consumption by up to 60% compared to traditional self-attention-based transformers.
• Score: 6.835244697120131
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based Super-Resolution (SR) models have recently advanced image reconstruction quality, yet challenges remain due to computational complexity and an over-reliance on large patch sizes, which constrain fine-grained detail enhancement. In this work, we propose TaylorIR to address these limitations by utilizing a patch size of 1x1, enabling pixel-level processing in any transformer-based SR model. To address the significant computational demands under the traditional self-attention mechanism, we employ the TaylorShift attention mechanism, a memory-efficient alternative based on Taylor series expansion, achieving full token-to-token interactions with linear complexity. Experimental results demonstrate that our approach achieves new state-of-the-art SR performance while reducing memory consumption by up to 60% compared to traditional self-attention-based transformers.

Related papers

• WaveHiT-SR: Hierarchical Wavelet Network for Efficient Image Super-Resolution [44.55918322585521]
  We propose a new approach by embedding the wavelet transform within a hierarchical transformer framework, called (WaveHiT-SR)<n>By progressively reconstructing high-resolution images through hierarchical processing, the network reduces computational complexity without sacrificing performance.<n>Our refined versions of SwinIR-Light, SwinIR-NG, and SRFormer-Light deliver cutting-edge SR results, achieving higher efficiency with fewer parameters, lower FLOPs, and faster speeds.
  arXiv  Detail & Related papers  (2025-08-27T14:37:50Z)
• Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention [54.42902794496325]
  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.
  arXiv  Detail & Related papers  (2025-05-22T02:57:23Z)
• FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution [21.909175743080713]
  Image super-resolution (SR) aims to recover low-resolution images to high-resolution images, where improving SR efficiency is a high-profile challenge. Commonly used units in SR, like convolutions and window-based Transformers, have limited receptive fields. We propose a Fourier token-based plugin called FourierSR to improve SR uniformly.
  arXiv  Detail & Related papers  (2025-03-13T04:50:55Z)
• Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling [50.34513854725803]
  Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors.<n>We propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-03-09T13:43:57Z)
• Contrast: A Hybrid Architecture of Transformers and State Space Models for Low-Level Vision [3.574664325523221]
  We propose textbfContrast, a hybrid SR model that combines textbfConvolutional, textbfTransformer, and textbfState Space components.<n>By integrating transformer and state space mechanisms, textbfContrast compensates for the shortcomings of each approach, enhancing both global context modeling and pixel-level accuracy.
  arXiv  Detail & Related papers  (2025-01-23T03:34:14Z)
• MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration [85.41380152286479]
  Experimental results across diverse image restoration benchmarks demonstrate that MB-TaylorFormer V2 achieves state-of-the-art performance in multiple image restoration tasks. The proposed model, named the second version of Taylor formula expansion-based Transformer (for short MB-TaylorFormer V2), has the capability to concurrently process coarse-to-fine features.
  arXiv  Detail & Related papers  (2025-01-08T13:13:52Z)
• HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution [70.52256118833583]
  We present a strategy to convert transformer-based SR networks to hierarchical transformers (HiT-SR) Specifically, we first replace the commonly used fixed small windows with expanding hierarchical windows to aggregate features at different scales. Considering the intensive computation required for large windows, we further design a spatial-channel correlation method with linear complexity to window sizes.
  arXiv  Detail & Related papers  (2024-07-08T12:42:10Z)
• CFAT: Unleashing TriangularWindows for Image Super-resolution [5.130320840059732]
  Transformer-based models have revolutionized the field of image super-resolution (SR) We propose a non-overlapping triangular window technique that synchronously works with the rectangular one to mitigate boundary-level distortion. Our proposed model shows a significant 0.7 dB performance improvement over other state-of-the-art SR architectures.
  arXiv  Detail & Related papers  (2024-03-24T13:31:31Z)
• Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach [58.57026686186709]
  We introduce the Convolutional Transformer layer (ConvFormer) and propose a ConvFormer-based Super-Resolution network (CFSR) CFSR inherits the advantages of both convolution-based and transformer-based approaches. Experiments demonstrate that CFSR strikes an optimal balance between computational cost and performance.
  arXiv  Detail & Related papers  (2024-01-11T03:08:00Z)
• PTSR: Patch Translator for Image Super-Resolution [16.243363392717434]
  We propose a patch translator for image super-resolution (PTSR) to address this problem. The proposed PTSR is a transformer-based GAN network with no convolution operation. We introduce a novel patch translator module for regenerating the improved patches utilising multi-head attention.
  arXiv  Detail & Related papers  (2023-10-20T01:45:00Z)
• Reciprocal Attention Mixing Transformer for Lightweight Image Restoration [6.3159191692241095]
  We propose a lightweight image restoration network, Reciprocal Attention Mixing Transformer (RAMiT) It employs bi-dimensional (spatial and channel) self-attentions in parallel with different numbers of multi-heads. It achieves state-of-the-art performance on multiple lightweight IR tasks, including super-resolution, color denoising, grayscale denoising, low-light enhancement, and deraining.
  arXiv  Detail & Related papers  (2023-05-19T06:55:04Z)
• Vicinity Vision Transformer [53.43198716947792]
  We present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity. Our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous methods.
  arXiv  Detail & Related papers  (2022-06-21T17:33:53Z)
• Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution [50.10987776141901]
  Recent vision transformers along with self-attention have achieved promising results on various computer vision tasks. We introduce an effective hybrid architecture for super-resolution (SR) tasks, which leverages local features from CNNs and long-range dependencies captured by transformers. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-15T06:52:25Z)
• HRFormer: High-Resolution Transformer for Dense Prediction [99.6060997466614]
  We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks. We take advantage of the multi-resolution parallel design introduced in high-resolution convolutional networks (HRNet) We demonstrate the effectiveness of the High-Resolution Transformer on both human pose estimation and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-10-18T15:37:58Z)
• XCiT: Cross-Covariance Image Transformers [73.33400159139708]
  We propose a "transposed" version of self-attention that operates across feature channels rather than tokens. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images.
  arXiv  Detail & Related papers  (2021-06-17T17:33:35Z)
• Improved Transformer for High-Resolution GANs [69.42469272015481]
  We introduce two key ingredients to Transformer to address this challenge. We show in the experiments that the proposed HiT achieves state-of-the-art FID scores of 31.87 and 2.95 on unconditional ImageNet $128 times 128$ and FFHQ $256 times 256$, respectively.
  arXiv  Detail & Related papers  (2021-06-14T17:39:49Z)

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.