由于卷积神经网络(CNNS)在从大规模数据中进行了学习的可概括图像前沿执行井,因此这些模型已被广泛地应用于图像恢复和相关任务。最近,另一类神经架构,变形金刚表现出对自然语言和高级视觉任务的显着性能。虽然变压器模型减轻了CNNS的缺点(即,有限的接收领域并对输入内容而无关),但其计算复杂性以空间分辨率二次大转,因此可以对涉及高分辨率图像的大多数图像恢复任务应用得不可行。在这项工作中,我们通过在构建块(多头关注和前锋网络)中进行多个关键设计,提出了一种有效的变压器模型,使得它可以捕获远程像素相互作用,同时仍然适用于大图像。我们的模型,命名恢复变压器(RESTORMER),实现了最先进的结果,导致几种图像恢复任务,包括图像派生,单图像运动脱棕,散焦去纹(单图像和双像素数据)和图像去噪(高斯灰度/颜色去噪,真实的图像去噪)。源代码和预先训练的型号可在https://github.com/swz30/restormer上获得。
translated by 谷歌翻译
Image restoration tasks demand a complex balance between spatial details and high-level contextualized information while recovering images. In this paper, we propose a novel synergistic design that can optimally balance these competing goals. Our main proposal is a multi-stage architecture, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps. Specifically, our model first learns the contextualized features using encoder-decoder architectures and later combines them with a high-resolution branch that retains local information. At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features. A key ingredient in such a multi-stage architecture is the information exchange between different stages. To this end, we propose a twofaceted approach where the information is not only exchanged sequentially from early to late stages, but lateral connections between feature processing blocks also exist to avoid any loss of information. The resulting tightly interlinked multi-stage architecture, named as MPRNet, delivers strong performance gains on ten datasets across a range of tasks including image deraining, deblurring, and denoising. The source code and pre-trained models are available at https://github.com/swz30/MPRNet.
translated by 谷歌翻译
最近的变形金刚和多层Perceptron(MLP)模型的进展为计算机视觉任务提供了新的网络架构设计。虽然这些模型在许多愿景任务中被证明是有效的,但在图像识别之类的愿景中,仍然存在挑战,使他们适应低级视觉。支持高分辨率图像和本地注意力的局限性的不灵活性可能是使用变压器和MLP在图像恢复中的主要瓶颈。在这项工作中,我们介绍了一个多轴MLP基于MARIC的架构,称为Maxim,可用作用于图像处理任务的高效和灵活的通用视觉骨干。 Maxim使用UNET形的分层结构,并支持由空间门控MLP启用的远程交互。具体而言,Maxim包含两个基于MLP的构建块:多轴门控MLP,允许局部和全球视觉线索的高效和可扩展的空间混合,以及交叉栅栏,替代跨关注的替代方案 - 细分互补。这两个模块都仅基于MLP,而且还受益于全局和“全卷积”,两个属性对于图像处理是可取的。我们广泛的实验结果表明,所提出的Maxim模型在一系列图像处理任务中实现了十多个基准的最先进的性能,包括去噪,失败,派热,脱落和增强,同时需要更少或相当的数量参数和拖鞋而不是竞争模型。
translated by 谷歌翻译
在本文中,我们呈现了UFFORER,一种用于图像恢复的有效和高效的变换器架构,其中我们使用变压器块构建分层编码器解码器网络。在UFFAR中,有两个核心设计。首先,我们介绍了一个新颖的本地增强型窗口(Lewin)变压器块,其执行基于窗口的自我关注而不是全局自我关注。它显着降低了高分辨率特征映射的计算复杂性,同时捕获本地上下文。其次,我们提出了一种以多尺度空间偏置的形式提出了一种学习的多尺度恢复调制器,以调整UFFORER解码器的多个层中的特征。我们的调制器展示了卓越的能力,用于恢复各种图像恢复任务的详细信息,同时引入边缘额外参数和计算成本。通过这两个设计提供支持,UFFORER享有高能力,可以捕获本地和全局依赖性的图像恢复。为了评估我们的方法,在几种图像恢复任务中进行了广泛的实验,包括图像去噪,运动脱棕,散焦和污染物。没有钟声和口哨,与最先进的算法相比,我们的UFormer实现了卓越的性能或相当的性能。代码和模型可在https://github.com/zhendongwang6/uformer中找到。
translated by 谷歌翻译
卷积神经网络(CNN)和变压器在多媒体应用中取得了巨大成功。但是,几乎没有努力有效,有效地协调这两个架构以满足图像的范围。本文旨在统一这两种架构,以利用其学习优点来降低图像。特别是,CNN的局部连通性和翻译等效性以及变压器中自我注意力(SA)的全球聚合能力被完全利用用于特定的局部环境和全球结构表示。基于雨水分布揭示降解位置和程度的观察,我们在帮助背景恢复之前引入退化,并因此呈现关联细化方案。提出了一种新型的多输入注意模块(MAM),以将降雨的去除和背景恢复关联。此外,我们为模型配备了有效的深度可分离卷积,以学习特定的特征表示并权衡计算复杂性。广泛的实验表明,我们提出的方法(称为ELF)的表现平均比最先进的方法(MPRNET)优于0.25 dB,但仅占其计算成本和参数的11.7 \%和42.1 \%。源代码可从https://github.com/kuijiang94/magic-elf获得。
translated by 谷歌翻译
沿着整个空间尺寸聚集的全局空间统计数据广泛用于顶级性能图像恢复器。例如,在挤压和激发(SE)中采用的实例归一化(IN)中采用的实例归一化(IN)的平均值,方差,其被应用于MPRNet。本文首先显示在训练/测试阶段的基于补丁/全部图像的特征上聚合的统计分别可以分发非常不同,并导致图像恢复器中的性能下降。它已被以前的作品被广泛忽视。要解决此问题,我们提出了一种简单的方法,测试时将局部统计转换器(TLSC)替换为仅在测试时间中从全局到本地的统计聚合操作区域。如果没有再培训或芬降,我们的方法显着提高了图像恢复器的性能。特别是,通过将TLSC扩展到最先进的模型,MPRNET升压在GoPro数据集上的PSNR中的0.65 dB,实现了33.31dB,超过了先前的最佳结果0.6 dB。此外,我们只需将TLSC应用于高级视觉任务,即语义细分,并实现竞争结果。进行了广泛的数量和质量实验,以证明TLSC解决了边际成本的问题,同时显着获得。该代码可在https://github.com/megvii-research/tlsc中获得。
translated by 谷歌翻译
As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing pipeline. In this paper, we consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method. The core components of LLFormer are the axis-based multi-head self-attention and cross-layer attention fusion block, which significantly reduces the linear complexity. Extensive experiments on the new dataset and existing public datasets show that LLFormer outperforms state-of-the-art methods. We also show that employing existing LLIE methods trained on our benchmark as a pre-processing step significantly improves the performance of downstream tasks, e.g., face detection in low-light conditions. The source code and pre-trained models are available at https://github.com/TaoWangzj/LLFormer.
translated by 谷歌翻译
现实世界图像Denoising是一个实用的图像恢复问题,旨在从野外嘈杂的输入中获取干净的图像。最近,Vision Transformer(VIT)表现出强大的捕获远程依赖性的能力,许多研究人员试图将VIT应用于图像DeNosing任务。但是,现实世界的图像是一个孤立的框架,它使VIT构建了内部贴片的远程依赖性,该依赖性将图像分为贴片并混乱噪声模式和梯度连续性。在本文中,我们建议通过使用连续的小波滑动转换器来解决此问题,该小波滑动转换器在现实世界中构建频率对应关系,称为dnswin。具体而言,我们首先使用CNN编码器从嘈杂的输入图像中提取底部功能。 DNSWIN的关键是将高频和低频信息与功能和构建频率依赖性分开。为此,我们提出了小波滑动窗口变压器,该变压器利用离散的小波变换,自我注意力和逆离散小波变换来提取深度特征。最后,我们使用CNN解码器将深度特征重建为DeNo的图像。对现实世界的基准测试的定量和定性评估都表明,拟议的DNSWIN对最新方法的表现良好。
translated by 谷歌翻译
否决单图是一项普遍但又具有挑战性的任务。复杂的降雪降解和各种降解量表需要强大的代表能力。为了使否定的网络看到各种降雪并建模本地细节和全球信息的上下文相互作用,我们提出了一种称为Snowformer的功能强大的建筑。首先,它在编码器中执行比例感知功能聚合,以捕获各种降解的丰富积雪信息。其次,为了解决大规模降级,它使用了解码器中的新颖上下文交互变压器块,该互动器块在全球上下文交互中从前范围内的局部细节和全局信息进行了上下文交互。并引入本地上下文互动可改善场景细节的恢复。第三,我们设计了一个异质的特征投影头,该功能投影头逐渐融合了编码器和解码器的特征,并将精制功能投影到干净的图像中。广泛的实验表明,所提出的雪诺形雪孔比其他SOTA方法取得了重大改进。与SOTA单图像HDCW-NET相比,它在CSD测试集上将PSNR度量提高了9.2dB。此外,与一般图像恢复体系结构NAFNET相比,PSNR的增加5.13db,这验证了我们的雪诺形雪地降雪任务的强大表示能力。该代码在\ url {https://github.com/ephemeral182/snowformer}中发布。
translated by 谷歌翻译
卷积神经网络(CNNS)成功地进行了压缩图像感测。然而,由于局部性和重量共享的归纳偏差,卷积操作证明了建模远程依赖性的内在限制。变压器,最初作为序列到序列模型设计,在捕获由于基于自我关注的架构而捕获的全局背景中,即使它可以配备有限的本地化能力。本文提出了一种混合框架,一个混合框架,其集成了从CNN提供的借用的优点以及变压器提供的全局上下文,以获得增强的表示学习。所提出的方法是由自适应采样和恢复组成的端到端压缩图像感测方法。在采样模块中,通过学习的采样矩阵测量图像逐块。在重建阶段,将测量投射到双杆中。一个是用于通过卷积建模邻域关系的CNN杆,另一个是用于采用全球自我关注机制的变压器杆。双分支结构是并发,并且本地特征和全局表示在不同的分辨率下融合,以最大化功能的互补性。此外,我们探索一个渐进的战略和基于窗口的变压器块,以降低参数和计算复杂性。实验结果表明了基于专用变压器的架构进行压缩感测的有效性,与不同数据集的最先进方法相比,实现了卓越的性能。
translated by 谷歌翻译
Image super-resolution (SR) serves as a fundamental tool for the processing and transmission of multimedia data. Recently, Transformer-based models have achieved competitive performances in image SR. They divide images into fixed-size patches and apply self-attention on these patches to model long-range dependencies among pixels. However, this architecture design is originated for high-level vision tasks, which lacks design guideline from SR knowledge. In this paper, we aim to design a new attention block whose insights are from the interpretation of Local Attribution Map (LAM) for SR networks. Specifically, LAM presents a hierarchical importance map where the most important pixels are located in a fine area of a patch and some less important pixels are spread in a coarse area of the whole image. To access pixels in the coarse area, instead of using a very large patch size, we propose a lightweight Global Pixel Access (GPA) module that applies cross-attention with the most similar patch in an image. In the fine area, we use an Intra-Patch Self-Attention (IPSA) module to model long-range pixel dependencies in a local patch, and then a $3\times3$ convolution is applied to process the finest details. In addition, a Cascaded Patch Division (CPD) strategy is proposed to enhance perceptual quality of recovered images. Extensive experiments suggest that our method outperforms state-of-the-art lightweight SR methods by a large margin. Code is available at https://github.com/passerer/HPINet.
translated by 谷歌翻译
Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from lowquality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by up to 0.14∼0.45dB, while the total number of parameters can be reduced by up to 67%.
translated by 谷歌翻译
在恶劣天气下降雪场景的图像恢复是一项艰巨的任务。雪图像具有复杂的降解,并在干净的图像上混乱,改变了干净的图像的分布。以前基于CNN的方法由于缺乏特定的全球建模能力,因此在恢复雪场景中完全恢复了雪场的挑战。在本文中,我们将视觉变压器应用于从单个图像中去除积雪的任务。具体而言,我们建议沿通道拆分的并行网络体系结构分别执行本地功能改进和全局信息建模。我们利用频道洗牌操作来结合其各自的优势以增强网络性能。其次,我们提出了MSP模块,该模块利用多规模的AVGPOOL来汇总不同大小的信息,并同时对多头自我注意力进行多尺度投影自我注意,以提高模型在不同规模下降下的表示能力。最后,我们设计了一个轻巧,简单的本地捕获模块,可以完善模型的本地捕获能力。在实验部分,我们进行了广泛的实验以证明我们方法的优越性。我们比较了三个雪场数据集上的先前清除方法。实验结果表明,我们的方法超过了更少的参数和计算的最新方法。在CSD测试数据集上,我们实现了1.99dB和SSIM 0.03的实质增长。在SRR和SNOW100K数据集上,与Transweather方法相比,我们还增加了2.47dB和1.62dB,在SSIM中提高了0.03。在视觉比较部分中,我们的MSP形式比现有方法获得了更好的视觉效果,证明了我们方法的可用性。
translated by 谷歌翻译
Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit self-attention computation within non-overlapping windows. However, each group of tokens are always from a dense area of the image. This is considered as a dense attention strategy since the interactions of tokens are restrained in dense regions. Obviously, this strategy could result in restricted receptive fields. To address this issue, we propose Attention Retractable Transformer (ART) for image restoration, which presents both dense and sparse attention modules in the network. The sparse attention module allows tokens from sparse areas to interact and thus provides a wider receptive field. Furthermore, the alternating application of dense and sparse attention modules greatly enhances representation ability of Transformer while providing retractable attention on the input image.We conduct extensive experiments on image super-resolution, denoising, and JPEG compression artifact reduction tasks. Experimental results validate that our proposed ART outperforms state-of-the-art methods on various benchmark datasets both quantitatively and visually. We also provide code and models at the website https://github.com/gladzhang/ART.
translated by 谷歌翻译
压缩在通过限制系统(例如流媒体服务,虚拟现实或视频游戏)等系统的有效传输和存储图像和视频中起着重要作用。但是,不可避免地会导致伪影和原始信息的丢失,这可能会严重降低视觉质量。由于这些原因,压缩图像的质量增强已成为流行的研究主题。尽管大多数最先进的图像恢复方法基于卷积神经网络,但基于Swinir等其他基于变压器的方法在这些任务上表现出令人印象深刻的性能。在本文中,我们探索了新型的Swin Transformer V2,以改善图像超分辨率的Swinir,尤其是压缩输入方案。使用这种方法,我们可以解决训练变压器视觉模型中的主要问题,例如训练不稳定性,预训练和微调之间的分辨率差距以及数据饥饿。我们对三个代表性任务进行实验:JPEG压缩伪像去除,图像超分辨率(经典和轻巧)以及压缩的图像超分辨率。实验结果表明,我们的方法SWIN2SR可以改善SWINIR的训练收敛性和性能,并且是“ AIM 2022挑战压缩图像和视频的超分辨率”的前5个解决方案。
translated by 谷歌翻译
Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities (e.g., images, videos, text and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. We then cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering, visual reasoning, and visual grounding), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution, image enhancement, and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works. We hope this effort will ignite further interest in the community to solve current challenges towards the application of transformer models in computer vision.
translated by 谷歌翻译
偏光颜色摄影在一个快照中提供视觉纹理和对象表面信息。但是,与常规颜色成像相比,定向偏振阵列的使用会导致极低的光子计数和SNR。因此,该特征实质上导致令人不愉快的嘈杂图像并破坏极化分析性能。对于传统的图像处理管道来说,这是一个挑战,因为事实是,隐式施加在渠道中的物理约束过于复杂。为了解决这个问题,我们提出了一种基于学习的方法,以同时恢复清洁信号和精确的极化信息。捕获了配对的原始短期嘈杂和长期暴露参考图像的真实世界两极化的颜色图像数据集,以支持基于学习的管道。此外,我们采用视觉变压器的开发,并提出了一个混合变压器模型,用于偏光颜色图像denoising,即PocoFormer,以更好地恢复性能。大量的实验证明了所提出的方法的有效性和影响结果的关键因素。
translated by 谷歌翻译
用于深度卷积神经网络的视频插值的现有方法,因此遭受其内在限制,例如内部局限性核心权重和受限制的接收领域。为了解决这些问题,我们提出了一种基于变换器的视频插值框架,允许内容感知聚合权重,并考虑具有自我关注操作的远程依赖性。为避免全球自我关注的高计算成本,我们将当地注意的概念引入视频插值并将其扩展到空间域。此外,我们提出了一个节省时间的分离策略,以节省内存使用,这也提高了性能。此外,我们开发了一种多尺度帧合成方案,以充分实现变压器的潜力。广泛的实验证明了所提出的模型对最先进的方法来说,定量和定性地在各种基准数据集上进行定量和定性。
translated by 谷歌翻译
基于深度卷积神经网络(CNN)的单图像飞机方法已取得了重大成功。以前的方法致力于通过增加网络的深度和宽度来改善网络的性能。当前的方法着重于增加卷积内核的大小,以通过受益于更大的接受场来增强其性能。但是,直接增加卷积内核的大小会引入大量计算开销和参数。因此,本文设计了一个新型的大内核卷积驱动块(LKD块),该磁带(LKD块)由分解深度大核卷积块(DLKCB)和通道增强的进料前向前网络(CEFN)组成。设计的DLKCB可以将深度大的内核卷积分为较小的深度卷积和深度扩张的卷积,而无需引入大量参数和计算开销。同时,设计的CEFN将通道注意机制纳入馈电网络中,以利用重要的通道并增强鲁棒性。通过组合多个LKD块和上向下的采样模块,可以进行大内核卷积DeHaze网络(LKD-NET)。评估结果证明了设计的DLKCB和CEFN的有效性,而我们的LKD-NET优于最先进的功能。在SOTS室内数据集上,我们的LKD-NET极大地优于基于变压器的方法Dehamer,只有1.79%#PARAM和48.9%的FLOPS。我们的LKD-NET的源代码可在https://github.com/swu-cs-medialab/lkd-net上获得。
translated by 谷歌翻译
在动态场景中拍摄的图像可能包含不必要的运动模糊,从而大大降低视觉质量。这种模糊会导致短期和远程特定区域的平滑伪像,通常是方向性和不均匀的,很难去除。受到变压器在计算机视觉和图像处理任务的最新成功的启发,我们开发了Stripformer,这是一种基于变压器的体系结构,该体系结构构建了内部和跨条纹代币,以在水平和垂直方向上重新构建图像特征,以捕获模糊的模式,以不同于不同方向。它堆叠了隔离的内带和串间注意层,以揭示模糊的幅度。除了检测各种取向和幅度的区域特异性模式外,Stripformer还是一个令牌效率和参数有效的变压器模型,要求比Vanilla变压器更少的内存使用和计算成本要少得多,但在不依赖巨大训练数据的情况下工作得更好。实验结果表明,在动态场景中,脱衣舞素对最新模型的表现良好。
translated by 谷歌翻译