Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion estimation modules due to the lack of a dataset containing pairs of videos with similar perspective but different motion. Therefore, the deep learning approaches for this task have difficulties in the pixel-level synthesis of latent stabilized frames, and resort to motion estimation modules for indirect transformations of the unstable frames to stabilized frames, leading to the loss of visual content near the frame boundaries. In this work, we aim to declutter this over-complicated formulation of video stabilization with the help of a novel dataset that contains pairs of training videos with similar perspective but different motion, and verify its effectiveness by successfully learning motion blind full-frame video stabilization through employing strictly conventional generative techniques and further improve the stability through a curriculum-learning inspired adversarial training strategy. Through extensive experimentation, we show the quantitative and qualitative advantages of the proposed approach to the state-of-the-art video stabilization approaches. Moreover, our method achieves $\sim3\times$ speed-up over the currently available fastest video stabilization methods.
The Hong Kong University of Science and Technology（香港科技大学）
Applying image processing algorithms independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our method is only trained on a pair of original and processed videos directly instead of a large dataset. Unlike most previous methods that enforce temporal consistency with optical flow, we show that temporal consistency can be achieved by training a convolutional network on a video with the Deep Video Prior. Moreover, a carefully designed iteratively reweighted…
National Taiwan University（国立台湾大学）；Google（谷歌）；UC Merced（加州大学默塞德分校）；Yonsei University（延世大学）；Virginia Tech（弗吉尼亚理工大学）
Existing video stabilization methods often generate visible distortion or require aggressive cropping of frame boundaries, resulting in smaller field of views. In this work, we present a frame synthesis algorithm to achieve full-frame video stabilization. We first estimate dense warp fields from neighboring frames and then synthesize the stabilized frame by fusing the warped contents. Our core technical novelty lies in the learning-based hybrid-space fusion that alleviates artifacts caused by optical flow inaccuracy and fast-moving objects. We validate the effectiveness of our method on the NU…
University of California San Diego（加州大学圣地亚哥分校）；Qualcomm Technologies Inc.（高通技术公司）；JD AI Research（京东人工智能研究院）
We propose a novel real-time selfie video stabilization method. Our method is completely automatic and runs at 26 fps. We use a 1D linear convolutional network to directly infer the rigid moving least squares warping which implicitly balances between the global rigidity and local flexibility. Our network structure is specifically designed to stabilize the background and foreground at the same time, while providing optional control of stabilization focus (relative importance of foreground vs. background) to the users. To train our network, we collect a selfie video dataset with 1005 videos, whi…
Videos are a popular media form, where online video streaming has recently gathered much popularity. In this work, we propose a novel method of real-time video stabilization - transforming a shaky video to a stabilized video as if it were stabilized via gimbals in real-time. Our framework is trainable in a self-supervised manner, which does not require data captured with special hardware setups (i.e., two cameras on a stereo rig or additional motion sensors). Our framework consists of a transformation estimator between given frames for global stability adjustments, followed by scene parallax r…
National University of Singapore（新加坡国立大学）；Temasek Laboratories（淡马锡实验室）
This paper describes the development of a novel algorithm to tackle the problem of real-time video stabilization for unmanned aerial vehicles (UAVs). There are two main components in the algorithm: (1) By designing a suitable model for the global motion of UAV, the proposed algorithm avoids the necessity of estimating the most general motion model, projective transformation, and considers simpler motion models, such as rigid transformation and similarity transformation. (2) To achieve a high processing speed, optical-flow based tracking is employed in lieu of conventional tracking and matching…
Most conventional supervised super-resolution (SR) algorithms assume that low-resolution (LR) data is obtained by downscaling high-resolution (HR) data with a fixed known kernel, but such an assumption often does not hold in real scenarios. Some recent blind SR algorithms have been proposed to estimate different downscaling kernels for each input LR image. However, they suffer from heavy computational overhead, making them infeasible for direct application to videos. In this work, we present DynaVSR, a novel meta-learning-based framework for real-world video SR that enables efficient downscali…
With the recent advent of methods that allow for real-time computation, dense 3D flows have become a viable basis for fast camera motion estimation. Most importantly, dense flows are more robust than the sparse feature matching techniques used by existing 3D stabilization methods, able to better handle large camera displacements and occlusions similar to those often found in consumer videos. Here we introduce a framework for 3D video stabilization that relies on dense scene flow alone. The foundation of this approach is a novel camera motion model that allows for real-world camera poses to be …
No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors
School of Electronic and Optical Engineering, Nanjing University of Science and Technology（南京理工大学电子与光学工程学院）；College of Geoexploration Science and Technology, Jilin University（吉林大学地球探测科学与技术学院）
We propose a self-supervised approach for training multi-frame video denoising networks. These networks predict frame t from a window of frames around t. Our self-supervised approach benefits from the video temporal consistency by penalizing a loss between the predicted frame t and a neighboring target frame, which are aligned using an optical flow. We use the proposed strategy for online internal learning, where a pre-trained network is fine-tuned to denoise a new unknown noise type from a single video. After a few frames, the proposed fine-tuning reaches and sometimes surpasses the performan…
Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task. In this paper we propose a fully blind video denoising method, with two versions off-line and on-line. This is achieved by fine-tuning a pre-trained AWGN denoising network to the video with a novel frame-to-frame training strategy. Our denoiser can be used without knowledge of the origin of the video or burst and the post processing steps applied from the camera sensor. The on-line process only req…
In conventional electronic video stabilization, the stabilized frame is obtained by cropping the input frame to cancel camera shake. While a small cropping size results in strong stabilization, it does not provide us satisfactory results from the viewpoint of image quality, because it narrows the angle of view. By fusing several frames, we can effectively expand the area of input frames, and achieve strong stabilization even with a large cropping size. Several methods for doing so have been studied. However, their computational costs are too high for embedded systems such as smartphones. We pr…
We propose ViDeNN: a CNN for Video Denoising without prior knowledge on the noise distribution (blind denoising). The CNN architecture uses a combination of spatial and temporal filtering, learning to spatially denoise the frames first and at the same time how to combine their temporal information, handling objects motion, brightness changes, low-light conditions and temporal inconsistencies. We demonstrate the importance of the data used for CNNs training, creating for this purpose a specific dataset for low-light conditions. We test ViDeNN on common benchmarks and on self-collected data, ach…
CAIR, HKISI-CAS（中国科学院香港创新研究院 中央美术学院视觉艺术高精尖创新中心）；Princeton University（普林斯顿大学）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；HKUST（香港科技大学）
Many videos contain flickering artifacts. Common causes of flicker include video processing algorithms, video generation algorithms, and capturing videos under specific situations. Prior work usually requires specific guidance such as the flickering frequency, manual annotations, or extra consistent videos to remove the flicker. In this work, we propose a general flicker removal framework that only receives a single flickering video as input without additional guidance. Since it is blind to a specific flickering type or guidance, we name this "blind deflickering." The core of our approach is u…
Blind video decaptioning is a problem of automatically removing text overlays and inpainting the occluded parts in videos without any input masks. While recent deep learning based inpainting methods deal with a single image and mostly assume that the positions of the corrupted pixels are known, we aim at automatic text removal in video sequences without mask information. In this paper, we propose a simple yet effective framework for fast blind video decaptioning. We construct an encoder-decoder model, where the encoder takes multiple source frames that can provide visible pixels revealed from …
Nanjing University of Science and Technology（南京理工大学）
Existing deep learning-based video super-resolution (SR) methods usually depend on the supervised learning approach, where the training data is usually generated by the blurring operation with known or predefined kernels (e.g., Bicubic kernel) followed by a decimation operation. However, this does not hold for real applications as the degradation process is complex and cannot be approximated by these idea cases well. Moreover, obtaining high-resolution (HR) videos and the corresponding low-resolution (LR) ones in real-world scenarios is difficult. To overcome these problems, we propose a self-…
University of Science and Technology of China（中国科学技术大学）
Video stabilization is essential for improving visual quality of shaky videos. The current video stabilization methods usually take feature trajectories in the background to estimate one global transformation matrix or several transformation matrices based on a fixed mesh, and warp shaky frames into their stabilized views. However, these methods may not model the shaky camera motion well in complicated scenes, such as scenes containing large foreground objects or strong parallax, and may result in notable visual artifacts in the stabilized videos. To resolve the above issues, this paper propos…
We present a deep neural network (DNN) that uses both sensor data (gyroscope) and image content (optical flow) to stabilize videos through unsupervised learning. The network fuses optical flow with real/virtual camera pose histories into a joint motion representation. Next, the LSTM block infers the new virtual camera pose, and this virtual pose is used to generate a warping grid that stabilizes the frame. Novel relative motion representation as well as a multi-stage training process are presented to optimize our model without any supervision. To the best of our knowledge, this is the first DN…
Video stabilization is a fundamental and important technique for higher quality videos. Prior works have extensively explored video stabilization, but most of them involve cropping of the frame boundaries and introduce moderate levels of distortion. We present a novel deep approach to video stabilization which can generate video frames without cropping and low distortion. The proposed framework utilizes frame interpolation techniques to generate in between frames, leading to reduced inter-frame jitter. Once applied in an iterative fashion, the stabilization effect becomes stronger. A major adv…
When trying to independently apply image-trained algorithms to successive frames in videos, noxious flickering tends to appear. State-of-the-art post-processing techniques that aim at fostering temporal consistency, generate other temporal artifacts and visually alter the style of videos. We propose a postprocessing model, agnostic to the transformation applied to videos (e.g. style transfer, image manipulation using GANs, etc.), in the form of a recurrent neural network. Our model is trained using a Ping Pong procedure and its corresponding loss, recently introduced for GAN video generation, …
Blind visual quality assessment (BVQA) on 360{\textdegree} video plays a key role in optimizing immersive multimedia systems. When assessing the quality of 360{\textdegree} video, human tends to perceive its quality degradation from the viewport-based spatial distortion of each spherical frame to motion artifact across adjacent frames, ending with the video-level quality score, i.e., a progressive quality assessment paradigm. However, the existing BVQA approaches for 360{\textdegree} video neglect this paradigm. In this paper, we take into account the progressive paradigm of human perception t…
Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization
School of Computing and Artificial Intelligence（计算与人工智能学院）；Southwest Jiaotong University（西南交通大学）；Department of Computer Science（计算机科学系）；Hanynag University（汉阳大学）；School of Computing and Augmented Intelligence（计算与增强智能学院）；Arizona State University（亚利桑那州立大学）
The University of Sydney（悉尼大学）；Birkbeck College（伯克贝克学院）
Previous deep learning-based video stabilizers require a large scale of paired unstable and stable videos for training, which are difficult to collect. Traditional trajectory-based stabilizers, on the other hand, divide the task into several sub-tasks and tackle them subsequently, which are fragile in textureless and occluded regions regarding the usage of hand-crafted features. In this paper, we attempt to tackle the video stabilization problem in a deep unsupervised learning manner, which borrows the divide-and-conquer idea from traditional stabilizers while leveraging the representation pow…
Hong Kong University of Science and Technology（香港科技大学）；Tencent Youtu（腾讯优图）
Video stabilization algorithms are of greater importance nowadays with the prevalence of hand-held devices which unavoidably produce videos with undesirable shaky motions. In this paper we propose a data-driven online video stabilization method along with a paired dataset for deep learning. The network processes each unsteady frame progressively in a multi-scale manner, from low resolution to high resolution, and then outputs an affine transformation to stabilize the frame. Different from conventional methods which require explicit feature tracking or optical flow estimation, the underlying st…
Discrete Prior-based Temporal-coherent Content Prediction for Blind Face Video Restoration
School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）；Institute of Super Robotics(Huangpu)（超级机器人（黄埔）研究院）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
Lancaster University（兰卡斯特大学）；Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）
Video stabilization plays a central role to improve videos quality. However, despite the substantial progress made by these methods, they were, mainly, tested under standard weather and lighting conditions, and may perform poorly under adverse conditions. In this paper, we propose a synthetic-aware adverse weather robust algorithm for video stabilization that does not require real data and can be trained only on synthetic data. We also present Silver, a novel rendering engine to generate the required training data with an automatic ground-truth extraction procedure. Our approach uses our speci…
TranStable: Towards Robust Pixel-level Online Video Stabilization by Jointing Transformer and CNN
Dalian University of Technology（大连理工大学）；Institute for Clarity in Documentation（文档清晰度研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗康分局）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
We present Steadiface, a new real-time face-centric video stabilization method that simultaneously removes hand shake and keeps subject's head stable. We use a CNN to estimate the face landmarks and use them to optimize a stabilized head center. We then formulate an optimization problem to find a virtual camera pose that locates the face to the stabilized head center while retains smooth rotation and translation transitions across frames. We test the proposed method on fieldtest videos and show it stabilizes both the head motion and background. It is robust to large head pose, occlusion, facia…
Determining Fetal Orientations From Blind Sweep Ultrasound Video
Technical University of Denmark（丹麦技术大学）；University of Copenhagen（哥本哈根大学）；Slagelse Hospital（斯劳厄尔瑟医院）；CAMES Rigshospitalet（CAMES 哥本哈根大学医院）；Pioneer Centre for AI（人工智能先锋中心）
Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual tasks and is unable to generalize to other applications. In this paper, we present an efficient end-to-end approach based on deep recurrent network for enforcing temporal consistency in a video. Our method takes the original unprocessed and per-frame processed videos as inputs to produce a temporally consistent video. Consequently, our approach is agnostic t…
Nanjing University of Science and Technology（南京理工大学）；SenseTime Research（商汤科技研究院）
Existing video super-resolution (SR) algorithms usually assume that the blur kernels in the degradation process are known and do not model the blur kernels in the restoration. However, this assumption does not hold for video SR and usually leads to over-smoothed super-resolved images. In this paper, we propose a deep convolutional neural network (CNN) model to solve video SR by a blur kernel modeling approach. The proposed deep CNN model consists of motion blur estimation, motion estimation, and latent image restoration modules. The motion blur estimation module is used to provide reliable blu…
Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos
The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；ARC Lab, Tencent PCG（腾讯平台与内容事业群ARC实验室）；The Guangdong University of Technology（广东工业大学）；Texas A&M University（德克萨斯农工大学）
Blind Quality Enhancement of Compressed Video via Fine-Grained Degradation-Guided Sequential Inference
School of Computer Science, Nanjing University of Information Science & Technology（南京信息工程大学计算机科学学院）；Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET)（江苏省大气环境与装备技术协同创新中心）；School of Software, Nanjing University of Information Science & Technology（南京信息工程大学软件学院）；department of Intelligent Science, Xi’an Jiaotong-Liverpool University（智能科学系，西安交通大学利物浦大学）；Department of Computing Sciences, Tampere University（计算科学系，塔尔基大学）；School of Computer Science, Nanjing University of Posts and Telecommunications（南京邮电大学计算机科学学院）
We present a method for stabilizing handheld video that simulates the camera motions cinematographers achieve with equipment like tripods, dollies, and Steadicams. We formulate a constrained convex optimization problem minimizing the $\ell_1$-norm of the first three derivatives of the stabilized motion. Our approach extends the work of Grundmann et al. [9] by solving with full homographies (rather than affinities) in order to correct perspective, preserving linearity by working in log-homography space. We also construct crop constraints that preserve field-of-view; model the problem as a quadr…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google Inc.（谷歌公司）
Many objective video quality assessment (VQA) algorithms include a key step of temporal pooling of frame-level quality scores. However, less attention has been paid to studying the relative efficiencies of different pooling methods on no-reference (blind) VQA. Here we conduct a large-scale comparative evaluation to assess the capabilities and limitations of multiple temporal pooling strategies on blind VQA of user-generated videos. The study yields insights and general guidance regarding the application and selection of temporal pooling models. In addition, we also propose an ensemble pooling …
The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
Warping-based video stabilizers smooth camera trajectory by constraining each pixel's displacement and warp stabilized frames from unstable ones accordingly. However, since the view outside the boundary is not available during warping, the resulting holes around the boundary of the stabilized frame must be discarded (i.e., cropping) to maintain visual consistency, and thus does leads to a tradeoff between stability and cropping ratio. In this paper, we make a first attempt to address this issue by proposing a new Out-of-boundary View Synthesis (OVS) method. By the nature of spatial coherence b…
State Key Laboratory of ASIC & System, College of Microelectronics, Fudan University（复旦大学微电子学院专用集成电路与系统国家重点实验室）；Laboratory for Image and Video Engineering (LIVE), Department of Electrical and Computer Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校电气与计算机工程系图像与视频工程实验室）
Video quality assessment (VQA) remains an important and challenging problem that affects many applications at the widest scales. Recent advances in mobile devices and cloud computing techniques have made it possible to capture, process, and share high resolution, high frame rate (HFR) videos across the Internet nearly instantaneously. Being able to monitor and control the quality of these streamed videos can enable the delivery of more enjoyable content and perceptually optimized rate control. Accordingly, there is a pressing need to develop VQA models that can be deployed at enormous scales. …
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（蒂宾根大学）
As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime. However, taking a quick shot frequently yields a blurry result due to unwanted camera shake during recording or moving objects in the scene. Removing these artifacts from the blurry recordings is a highly ill-posed problem as neither the sharp image nor the motion blur kernel is known. Propagating information between multiple consecutive blurry observations can help restore the desired sharp image or video. Solutions for blind deconvolution based on n…
Perceptual quality assessment of the videos acquired in the wilds is of vital importance for quality assurance of video services. The inaccessibility of reference videos with pristine quality and the complexity of authentic distortions pose great challenges for this kind of blind video quality assessment (BVQA) task. Although model-based transfer learning is an effective and efficient paradigm for the BVQA task, it remains to be a challenge to explore what and how to bridge the domain shifts for better video representation. In this work, we propose to transfer knowledge from image quality asse…
University of Cambridge（剑桥大学）；Samsung AI Center, Cambridge（三星剑桥人工智能中心）；University of Warwick（华威大学）
Deep learning-based blind super-resolution (SR) methods have recently achieved unprecedented performance in upscaling frames with unknown degradation. These models are able to accurately estimate the unknown downscaling kernel from a given low-resolution (LR) image in order to leverage the kernel during restoration. Although these approaches have largely been successful, they are predominantly image-based and therefore do not exploit the temporal properties of the kernels across multiple video frames. In this paper, we investigated the temporal properties of the kernels and highlighted its imp…
