Video super-resolution aims at generating a high-resolution video from its low-resolution counterpart. With the rapid rise of deep learning, many recently proposed video super-resolution methods use convolutional neural networks in conjunction with explicit motion compensation to capitalize on statistical dependencies within and across low-resolution frames. Two common issues of such methods are noteworthy. Firstly, the quality of the final reconstructed HR video is often very sensitive to the accuracy of motion estimation. Secondly, the warp grid needed for motion compensation, which is specified by the two flow maps delineating pixel displacements in horizontal and vertical directions, tends to introduce additional errors and jeopardize the temporal consistency across video frames. To address these issues, we propose a novel dynamic local filter network to perform implicit motion estimation and compensation by employing, via locally connected layers, sample-specific and position-specific dynamic local filters that are tailored to the target pixels. We also propose a global refinement network based on ResBlock and autoencoder structures to exploit non-local correlations and enhance the spatial consistency of super-resolved frames. The experimental results demonstrate that the proposed method outperforms the state-of-the-art, and validate its strength in terms of local transformation handling, temporal consistency as well as edge sharpness.
A Unified Theory of Sinusoidal Activation Families for Implicit Neural Representations
McGill University（麦吉尔大学）；University of Melbourne（墨尔本大学）；ARC Centre of Excellence for the Mathematical Analysis of Cellular Systems (MACSYS)（细胞系统数学分析卓越中心（MACSYS））；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University Health Network（大学健康网络）；University of Tehran（塔里斯坦大学）
Convolutional neural networks have enabled accurate image super-resolution in real-time. However, recent attempts to benefit from temporal correlations in video super-resolution have been limited to naive or inefficient architectures. In this paper, we introduce spatio-temporal sub-pixel convolution networks that effectively exploit temporal redundancies and improve reconstruction accuracy while maintaining real-time speed. Specifically, we discuss the use of early fusion, slow fusion and 3D convolutions for the joint processing of multiple consecutive video frames. We also propose a novel joi…
Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation
Hefei University of Technology（合肥工业大学）；Hangzhou Dianzi University（杭州电子科技大学）；Jinan University（吉林大学）；South China Agricultural University（华南农业大学）；The University of Tokyo（东京大学）
Nankai University（南开大学）；The Hongkong University of Science and Technology（香港科技大学）
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-parameterization mechanism, named representation compensation (RC) module, to decouple the representation learning of both old and new knowledge. The RC module consists of two dynamically evolved branches with one frozen and one trainable. Besides, we design a pooled cube knowledge distillation strategy on both spatial and channel dimensions to further enhance the plasticity and …
Video super-resolution (SR) aims to generate a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The generation of accurate correspondence plays a significant role in video SR. It is demonstrated by traditional video SR methods that simultaneous SR of both images and optical flows can provide accurate correspondences and better SR results. However, LR optical flows are used in existing deep learning based methods for correspondence generation. In this paper, we propose an end-to-end trainable video SR framework…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Google（谷歌）
Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current state-of-the-art methods process a batch of LR frames to generate a single high-resolution (HR) frame and run this scheme in a sliding window fashion over the entire video, effectively treating the problem as a large number of separate multi-frame super-resolution tasks. This approach has two main weaknesses: 1) Each input frame is processed and warped multiple ti…
Differentiable Score-Based Likelihoods: Learning CT Motion Compensation From Clean Images
Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大-埃尔朗根-纽伦堡大学）；Fraunhofer Institute for Ceramic Technologies and Systems IKTS（弗劳恩霍夫陶瓷技术与系统研究所IKTS）
We propose a method to compress full-resolution video sequences with implicit neural representations. Each frame is represented as a neural network that maps coordinate positions to pixel values. We use a separate implicit network to modulate the coordinate inputs, which enables efficient motion compensation between frames. Together with a small residual network, this allows us to efficiently compress P-frames relative to the previous frame. We further lower the bitrate by storing the network weights with learned integer quantization. Our method, which we call implicit pixel flow (IPF), offers…
Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well concerned, summarized and utilized for guidance in a VSR algorithm. Especially, when a video contains large motion, conventional methods easily bring incoherent results or artifacts. In this paper, we propose a novel deep neural network with Dual Subnet and Multi-stage Communicated Upsampling (DSMC) for super-resolution of videos with large motion. We design a…
University of Kansas（堪萨斯大学）；Worcester Polytechnic Institute（伍斯特理工学院）；Ryerson University（瑞尔森大学）
Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn to denoise the (attacked) point clouds by reconstruction, and then feed them to the classifiers as input. In contrast to the literature, we propose a family of robust structured declarative classifiers for point cloud classification, where the internal constrained optimization mechanism can effectively defend adversarial attacks through implicit gradients. Such classifiers can be formulated using a bilevel optimizati…
Wrocław University of Science and Technology（沃拉夫大学科学与技术学院）；Poznań University of Technology（波兹南技术大学）；IDEAS Research Institute（IDEAS研究所）；Jagiellonian University（雅盖隆大学）
Nanjing University（南京大学）；New York University（纽约大学）
Over the past two decades, traditional block-based video coding has made remarkable progress and spawned a series of well-known standards such as MPEG-4, H.264/AVC and H.265/HEVC. On the other hand, deep neural networks (DNNs) have shown their powerful capacity for visual content understanding, feature extraction and compact representation. Some previous works have explored the learnt video coding algorithms in an end-to-end manner, which show the great potential compared with traditional methods. In this paper, we propose an end-to-end deep neural video coding framework (NVC), which uses vari…
University of Southern California（南加州大学）；Facebook AI Research（Facebook人工智能研究院）；Facebook Reality Labs（Facebook现实实验室）
Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks. Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images. We argue that this limitation stems primarily form two conflicting requirements; accurate predictions require large context, but precise predictions require high resolution. Due to memory limitations in current hardware, previous approaches tend to t…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Robert Bosch Center for Data Science and AI（罗伯特·博世数据科学与人工智能中心）
Deep convolutional neural networks (CNNs) for video denoising are typically trained with supervision, assuming the availability of clean videos. However, in many applications, such as microscopy, noiseless videos are not available. To address this, we propose an Unsupervised Deep Video Denoiser (UDVD), a CNN architecture designed to be trained exclusively with noisy data. The performance of UDVD is comparable to the supervised state-of-the-art, even when trained only on a single short noisy video. We demonstrate the promise of our approach in real-world imaging applications by denoising raw vi…
Deformable Feature Alignment and Refinement for Moving Infrared Dim-small Target Detection
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）
Predicting the future is an important aspect for decision-making in robotics or autonomous driving systems, which heavily rely upon visual scene understanding. While prior work attempts to predict future video pixels, anticipate activities or forecast future scene semantic segments from segmentation of the preceding frames, methods that predict future semantic segmentation solely from the previous frame RGB data in a single end-to-end trainable model do not exist. In this paper, we propose a temporal encoder-decoder network architecture that encodes RGB frames from the past and decodes the fut…
CWRNN-INVR: A Coupled WarpRNN based Implicit Neural Video Representation
School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；Key Laboratory of Machine Intelligence and System Control, Ministry of Education（教育部机器智能与系统控制重点实验室）；School of Software, Shandong University（山东大学软件学院）；Shandong University-WeiHai Research Institute of Industrial Technology（山东大学威海工业技术研究院）；University of Electronic Science and Technology of China（电子科技大学）；Institute of Microelectronics, Chinese Academy of Sciences（中国科学院微电子研究所）
University of California at Merced（加州大学默塞德分校）；Carnegie Mellon University（卡内基梅隆大学）
Analyzing videos of human actions involves understanding the temporal relationships among video frames. State-of-the-art action recognition approaches rely on traditional optical flow estimation methods to pre-compute motion information for CNNs. Such a two-stage approach is computationally expensive, storage demanding, and not end-to-end trainable. In this paper, we present a novel CNN architecture that implicitly captures motion information between adjacent frames. We name our approach hidden two-stream CNNs because it only takes raw video frames as input and directly predicts action classes…
