最近,与常规像素的隐性表示相比,视频的图像隐式神经表示,其有希望的结果和迅速的速度因其有希望的结果和迅速的速度而受欢迎。但是,网络结构内的冗余参数在扩大理想性能时会导致大型模型大小。这种现象的关键原因是神经的耦合公式,该公式直接从框架索引输入中输出视频帧的空间和时间信息。在本文中,我们提出了E-NERV,它通过将图像的隐式神经代表分解为单独的空间和时间上下文来显着加快神经的速度。在这种新公式的指导下,我们的模型大大降低了冗余模型参数,同时保留表示能力。我们从实验上发现,我们的方法可以通过更少的参数改善性能,从而使收敛的速度更快地提高了$ 8 \ times $。代码可在https://github.com/kyleleey/e-nerv上找到。
translated by 谷歌翻译
我们研究如何代表具有隐式神经表示(INRS)的视频。经典INRS方法通常利用MLP将输入坐标映射到输出像素。尽管最近的一些作品试图直接使用CNN重建整个图像。但是,我们认为,以上像素和图像策略都不利于视频数据。取而代之的是,我们提出了一个贴片解决方案PS-NERV,该解决方案将视频表示为贴片的函数和相应的补丁坐标。它自然继承了图像方法的优势,并以快速解码速度实现出色的重建性能。整个方法包括常规模块,例如位置嵌入,MLP和CNN,同时还引入了ADAIN以增强中间特征。这些简单而基本的更改可以帮助网络轻松拟合高频细节。广泛的实验证明了其在几个与视频有关的任务中的有效性,例如视频压缩和视频介绍。
translated by 谷歌翻译
视频通常将流和连续的视觉数据记录为离散的连续帧。由于存储成本对于高保真度的视频来说是昂贵的,因此大多数存储以相对较低的分辨率和帧速率存储。最新的时空视频超分辨率(STVSR)的工作是开发出来的,以将时间插值和空间超分辨率纳入统一框架。但是,其中大多数仅支持固定的上采样量表,这限制了其灵活性和应用。在这项工作中,我们没有遵循离散表示,我们提出了视频隐式神经表示(videoinr),并显示了其对STVSR的应用。学到的隐式神经表示可以解码为任意空间分辨率和帧速率的视频。我们表明,Videoinr在常见的上采样量表上使用最先进的STVSR方法实现了竞争性能,并且在连续和训练的分布量表上显着优于先前的作品。我们的项目页面位于http://zeyuan-chen.com/videoinr/。
translated by 谷歌翻译
Neural fields, also known as coordinate-based or implicit neural representations, have shown a remarkable capability of representing, generating, and manipulating various forms of signals. For video representations, however, mapping pixel-wise coordinates to RGB colors has shown relatively low compression performance and slow convergence and inference speed. Frame-wise video representation, which maps a temporal coordinate to its entire frame, has recently emerged as an alternative method to represent videos, improving compression rates and encoding speed. While promising, it has still failed to reach the performance of state-of-the-art video compression algorithms. In this work, we propose FFNeRV, a novel method for incorporating flow information into frame-wise representations to exploit the temporal redundancy across the frames in videos inspired by the standard video codecs. Furthermore, we introduce a fully convolutional architecture, enabled by one-dimensional temporal grids, improving the continuity of spatial features. Experimental results show that FFNeRV yields the best performance for video compression and frame interpolation among the methods using frame-wise representations or neural fields. To reduce the model size even further, we devise a more compact convolutional architecture using the group and pointwise convolutions. With model compression techniques, including quantization-aware training and entropy coding, FFNeRV outperforms widely-used standard video codecs (H.264 and HEVC) and performs on par with state-of-the-art video compression algorithms.
translated by 谷歌翻译
Implicit Neural Representations (INR) have recently shown to be powerful tool for high-quality video compression. However, existing works are limiting as they do not explicitly exploit the temporal redundancy in videos, leading to a long encoding time. Additionally, these methods have fixed architectures which do not scale to longer videos or higher resolutions. To address these issues, we propose NIRVANA, which treats videos as groups of frames and fits separate networks to each group performing patch-wise prediction. This design shares computation within each group, in the spatial and temporal dimensions, resulting in reduced encoding time of the video. The video representation is modeled autoregressively, with networks fit on a current group initialized using weights from the previous group's model. To further enhance efficiency, we perform quantization of the network parameters during training, requiring no post-hoc pruning or quantization. When compared with previous works on the benchmark UVG dataset, NIRVANA improves encoding quality from 37.36 to 37.70 (in terms of PSNR) and the encoding speed by 12X, while maintaining the same compression rate. In contrast to prior video INR works which struggle with larger resolution and longer videos, we show that our algorithm is highly flexible and scales naturally due to its patch-wise and autoregressive designs. Moreover, our method achieves variable bitrate compression by adapting to videos with varying inter-frame motion. NIRVANA achieves 6X decoding speed and scales well with more GPUs, making it practical for various deployment scenarios.
translated by 谷歌翻译
Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation attention mechanism is proposed to reduce the complexity of standard Transformers. Then, a full autoregressive model, a partial autoregressive model and a non-autoregressive model are developed based on the new efficient Transformer. The partial autoregressive model has a similar performance with the full autoregressive model but a faster inference speed. The non-autoregressive model not only achieves a faster inference speed but also mitigates the quality degradation problem of the autoregressive counterparts, but it requires additional parameters and loss function for learning. Given the same attention mechanism, we conducted a comprehensive study to compare the proposed three video prediction variants. Experiments show that the proposed video prediction models are competitive with more complex state-of-the-art convolutional-LSTM based models. The source code is available at https://github.com/XiYe20/VPTR.
translated by 谷歌翻译
神经领域已成为一种新的数据表示范式,并在各种信号表示中表现出了显着的成功。由于它们在网络参数中保留信号,因此通过发送和接收整个模型参数来传输数据传输,可以防止在许多实际情况下使用这种新兴技术。我们提出了流媒体神经场,这是一个由各种宽度的可执行子网络组成的单个模型。拟议的建筑和培训技术使一个网络能够随着时间的流逝而流式传输,并重建不同的素质和一部分信号。例如,较小的子网络会产生光滑和低频信号,而较大的子网络可以代表细节。实验结果显示了我们方法在各个域中的有效性,例如2D图像,视频和3D签名的距离函数。最后,我们证明我们提出的方法通过利用参数共享来提高培训稳定性。
translated by 谷歌翻译
有效地对视频中的空间信息进行建模对于动作识别至关重要。为了实现这一目标,最先进的方法通常采用卷积操作员和密集的相互作用模块,例如非本地块。但是,这些方法无法准确地符合视频中的各种事件。一方面,采用的卷积是有固定尺度的,因此在各种尺度的事件中挣扎。另一方面,密集的相互作用建模范式仅在动作 - 欧元零件时实现次优性能,给最终预测带来了其他噪音。在本文中,我们提出了一个统一的动作识别框架,以通过引入以下设计来研究视频内容的动态性质。首先,在提取本地提示时,我们会生成动态尺度的时空内核,以适应各种事件。其次,为了将这些线索准确地汇总为全局视频表示形式,我们建议仅通过变压器在一些选定的前景对象之间进行交互,从而产生稀疏的范式。我们将提出的框架称为事件自适应网络(EAN),因为这两个关键设计都适应输入视频内容。为了利用本地细分市场内的短期运动,我们提出了一种新颖有效的潜在运动代码(LMC)模块,进一步改善了框架的性能。在几个大规模视频数据集上进行了广泛的实验,例如,某种东西,动力学和潜水48,验证了我们的模型是否在低拖鞋上实现了最先进或竞争性的表演。代码可在:https://github.com/tianyuan168326/ean-pytorch中找到。
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
隐式神经表示(INR)被出现为代表信号的强大范例,例如图像,视频,3D形状等。尽管它已经示出了能够表示精细细节的能力,但其效率尚未得到广泛研究数据表示。在INR中,数据以神经网络的参数的形式存储,并且通用优化算法通常不会利用信号中的空间和时间冗余。在本文中,我们建议通过明确地删除数据冗余来表示和压缩视频的新型INR方法。我们提出了跨视频帧和残差的主体剩余流场(NRFF)而不是存储原始RGB颜色,而不是存储原始RGB颜色。维护通常更光滑和更复杂的运动信息,比原始信号更少,需要更少的参数。此外,重用冗余像素值进一步提高了网络参数效率。实验结果表明,所提出的方法优于基线方法的显着边际。代码可用于https://github.com/daniel03c1/eff_video_repruseentation。
translated by 谷歌翻译
由于大气湍流的扭曲而恢复图像是一个长期存在的问题,这是由于变形的空间变化,图像形成过程的非线性以及训练和测试数据的稀缺性。现有方法通常在失真模型上具有强大的统计假设,在许多情况下,由于没有概括,因此在现实世界中的性能有限。为了克服挑战,本文提出了一种端到端物理驱动的方法,该方法有效,可以推广到现实世界的湍流。在数据合成方面,我们通过通过宽sense式的平稳性近似随机场来显着增加SOTA湍流模拟器可以处理的图像分辨率。新的数据合成过程使大规模的多级湍流和训练的地面真相对产生。在网络设计方面,我们提出了湍流缓解变压器(TMT),这是一个两级U-NET形状的多帧恢复网络,该网络具有Noval有效的自发机制,称为暂时通道关节关注(TCJA)。我们还引入了一种新的培训方案,该方案由新的模拟器启用,并设计新的变压器单元以减少内存消耗。在静态场景和动态场景上的实验结果是有希望的,包括各种真实的湍流场景。
translated by 谷歌翻译
时空视频超分辨率(STVSR)的目标是增加低分辨率(LR)和低帧速率(LFR)视频的空间分辨率。基于深度学习的最新方法已取得了重大改进,但是其中大多数仅使用两个相邻帧,即短期功能,可以合成缺失的框架嵌入,这无法完全探索连续输入LR帧的信息流。此外,现有的STVSR模型几乎无法明确利用时间上下文以帮助高分辨率(HR)框架重建。为了解决这些问题,在本文中,我们提出了一个称为STDAN的可变形注意网络。首先,我们设计了一个长短的术语特征插值(LSTFI)模块,该模块能够通过双向RNN结构从更相邻的输入帧中挖掘大量的内容,以进行插值。其次,我们提出了一个空间 - 周期性变形特征聚合(STDFA)模块,其中动态视频框架中的空间和时间上下文被自适应地捕获并汇总以增强SR重建。几个数据集的实验结果表明,我们的方法的表现优于最先进的STVSR方法。该代码可在https://github.com/littlewhitesea/stdan上找到。
translated by 谷歌翻译
如今,由于屏幕共享,远程合作和在线教育的广泛应用,屏幕内容存在爆炸性增长。为了匹配有限终端带宽,可以缩小高分辨率(HR)屏幕内容并压缩。在接收器侧,低分辨率(LR)屏幕内容图像(SCI)的超分辨率(SR)由HR显示器或用户缩小以供详细观察。然而,由于图像特性非常不同的图像特性以及在任意尺度下浏览的SCI浏览要求,图像SR方法主要针对自然图像设计不概括SCI。为此,我们为SCISR提出了一种新颖的隐式变压器超分辨率网络(ITSRN)。对于任意比率的高质量连续SR,通过所提出的隐式变压器从密钥坐标处的图像特征推断出查询坐标处的像素值,并且提出了隐式位置编码方案来聚合与查询相似的相邻像素值。使用LR和HR SCI对构建基准SCI1K和SCI1K压缩数据集。广泛的实验表明,提出的ITSRN显着优于压缩和未压缩的SCI的几种竞争连续和离散SR方法。
translated by 谷歌翻译
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion features. In this work, we aim to efficiently encode these two features in a unified 2D framework. To this end, we first propose an STM block, which contains a Channel-wise SpatioTemporal Module (CSTM) to present the spatiotemporal features and a Channel-wise Motion Module (CMM) to efficiently encode motion features. We then replace original residual blocks in the ResNet architecture with STM blcoks to form a simple yet effective STM network by introducing very limited extra computation cost. Extensive experiments demonstrate that the proposed STM network outperforms the state-of-the-art methods on both temporal-related datasets (i.e., Something-Something v1 & v2 and Jester) and scene-related datasets (i.e., Kinetics-400, UCF-101, and HMDB-51) with the help of encoding spatiotemporal and motion features together. * The work was done during an internship at SenseTime.
translated by 谷歌翻译
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, the first end-to-end video object detection system based on spatial-temporal Transformer architectures. The first goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow model, relation networks. Besides, benefited from the object query design in DETR, our method does not need complicated post-processing methods such as Seq-NMS. In particular, we present a temporal Transformer to aggregate both the spatial object queries and the feature memories of each frame. Our temporal transformer consists of two components: Temporal Query Encoder (TQE) to fuse object queries, and Temporal Deformable Transformer Decoder (TDTD) to obtain current frame detection results. These designs boost the strong baseline deformable DETR by a significant margin (2 %-4 % mAP) on the ImageNet VID dataset. TransVOD yields comparable performances on the benchmark of ImageNet VID. Then, we present two improved versions of TransVOD including TransVOD++ and TransVOD Lite. The former fuses object-level information into object query via dynamic convolution while the latter models the entire video clips as the output to speed up the inference time. We give detailed analysis of all three models in the experiment part. In particular, our proposed TransVOD++ sets a new state-of-the-art record in terms of accuracy on ImageNet VID with 90.0 % mAP. Our proposed TransVOD Lite also achieves the best speed and accuracy trade-off with 83.7 % mAP while running at around 30 FPS on a single V100 GPU device. Code and models will be available for further research.
translated by 谷歌翻译
In recent years, the Transformer architecture has shown its superiority in the video-based person re-identification task. Inspired by video representation learning, these methods mainly focus on designing modules to extract informative spatial and temporal features. However, they are still limited in extracting local attributes and global identity information, which are critical for the person re-identification task. In this paper, we propose a novel Multi-Stage Spatial-Temporal Aggregation Transformer (MSTAT) with two novel designed proxy embedding modules to address the above issue. Specifically, MSTAT consists of three stages to encode the attribute-associated, the identity-associated, and the attribute-identity-associated information from the video clips, respectively, achieving the holistic perception of the input person. We combine the outputs of all the stages for the final identification. In practice, to save the computational cost, the Spatial-Temporal Aggregation (STA) modules are first adopted in each stage to conduct the self-attention operations along the spatial and temporal dimensions separately. We further introduce the Attribute-Aware and Identity-Aware Proxy embedding modules (AAP and IAP) to extract the informative and discriminative feature representations at different stages. All of them are realized by employing newly designed self-attention operations with specific meanings. Moreover, temporal patch shuffling is also introduced to further improve the robustness of the model. Extensive experimental results demonstrate the effectiveness of the proposed modules in extracting the informative and discriminative information from the videos, and illustrate the MSTAT can achieve state-of-the-art accuracies on various standard benchmarks.
translated by 谷歌翻译
基于常规卷积网络的视频超分辨率(VSR)方法具有很强的视频序列的时间建模能力。然而,在单向反复卷积网络中的不同反复单元接收的输入信息不平衡。早期重建帧接收较少的时间信息,导致模糊或工件效果。虽然双向反复卷积网络可以缓解这个问题,但它大大提高了重建时间和计算复杂性。它也不适用于许多应用方案,例如在线超分辨率。为了解决上述问题,我们提出了一种端到端信息预构建的经常性重建网络(IPRRN),由信息预构建网络(IPNet)和经常性重建网络(RRNET)组成。通过将足够的信息从视频的前面集成来构建初始复发单元所需的隐藏状态,以帮助恢复较早的帧,信息预构建的网络在不向后传播之前和之后的输入信息差异。此外,我们展示了一种紧凑的复发性重建网络,可显着改善恢复质量和时间效率。许多实验已经验证了我们所提出的网络的有效性,并与现有的最先进方法相比,我们的方法可以有效地实现更高的定量和定性评估性能。
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
时空视频超分辨率(STVSR)旨在从相应的低帧速率,低分辨率视频序列构建高空时间分辨率视频序列。灵感来自最近的成功,考虑空间时间超级分辨率的空间信息,我们在这项工作中的主要目标是在快速动态事件的视频序列中充分考虑空间和时间相关性。为此,我们提出了一种新颖的单级内存增强图注意网络(Megan),用于时空视频超分辨率。具体地,我们构建新颖的远程存储图聚合(LMGA)模块,以沿着特征映射的信道尺寸动态捕获相关性,并自适应地聚合信道特征以增强特征表示。我们介绍了一个非本地剩余块,其使每个通道明智的功能能够参加全局空间分层特征。此外,我们采用渐进式融合模块通过广泛利用来自多个帧的空间 - 时间相关性来进一步提高表示能力。实验结果表明,我们的方法与定量和视觉上的最先进的方法相比,实现了更好的结果。
translated by 谷歌翻译
中心位置是否完全能够代表像素?在离散的图像表示中表示具有它们的中心的像素的错误,但是在图像超分辨率(SR)上下文中的局域脉中的信号的聚合时,它更有意义地考虑每个像素。尽管任意级图像SR领域的基于坐标的隐式表示的能力很大,但该区域的像素的性质不完全考虑。为此,我们提出了集成的位置编码(IPE),通过聚合在像素区域上聚合频率信息来扩展传统的位置编码。我们将IPE应用于最先进的任意级图像超分辨率方法:本地隐式图像功能(LIIF),呈现IPE-LIIF。我们通过定量和定性评估显示IPE-LIIF的有效性,并进一步证明了IPE泛化能力与更大的图像尺度和基于多种隐式的方法。代码将被释放。
translated by 谷歌翻译