We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame is inverted in the latent space of StyleGAN, from which the optimal compression is learned. To do so, a diffeomorphic latent representation is learned using a normalizing flows model, where an entropy model can be optimized for image coding. In addition, we propose a new perceptual loss that is more efficient than other counterparts. Finally, an entropy model for video inter coding with residual is also learned in the previously constructed latent representation. Our method (SGANC) is simple, faster to train, and achieves better results for image and video coding compared to state-of-the-art codecs such as VTM, AV1, and recent deep learning techniques. In particular, it drastically minimizes perceptual distortion at low bit rates.
Recently, high-quality video conferencing with fewer transmission bits has become a very hot and challenging problem. We propose FAIVConf, a specially designed video compression framework for video conferencing, based on the effective neural human face generation techniques. FAIVConf brings together several designs to improve the system robustness in real video conference scenarios: face-swapping to avoid artifacts in background animation; facial blurring to decrease transmission bit-rate and maintain the quality of extracted facial landmarks; and dynamic source update for face view interpolation to accommodate a large range of head poses. Our method achieves a significant bit-rate reduction in the video conference and gives much better visual quality under the same bit-rate compared with H.264 and H.265 coding schemes.
Videos are prone to tampering attacks that alter the meaning and deceive the audience. Previous video forgery detection schemes find tiny clues to locate the tampered areas. However, attackers can successfully evade supervision by destroying such clues using video compression or blurring. This paper proposes a video watermarking network for tampering localization. We jointly train a 3D-UNet-based watermark embedding network and a decoder that predicts the tampering mask. The perturbation made by watermark embedding is close to imperceptible. Considering that there is no off-the-shelf differentiable video codec simulator, we propose to mimic video compression by ensembling simulation results of other typical attacks, e.g., JPEG compression and blurring, as an approximation. Experimental results demonstrate that our method generates watermarked videos with good imperceptibility and robustly and accurately locates tampered areas within the attacked version.
The global significance of energy consumption of video communication renders research on the energy need of video coding an important task. To do so, usually, a dedicated setup is needed that measures the energy of the encoding and decoding system. However, such measurements are costly and complex. To this end, this paper presents the results of an exhaustive measurement series using the x265 encoder implementation of HEVC and analyzes the relation between encoding time and encoding energy. Finally, we introduce a simple encoding energy estimation model which employs the encoding time of a lightweight encoding process to estimate the encoding energy of complex encoding configurations. The proposed model reaches a mean estimation error of 11.35% when averaged over all presets. The results from this work are useful when the encoding energy estimate is required to develop new energy-efficient video compression algorithms.
This paper presents improvements and novel additions to our recent work on end-to-end optimized hierarchical bi-directional video compression to further advance the state-of-the-art in learned video compression. As an improvement, we combine motion estimation and prediction modules and compress refined residual motion vectors for improved rate-distortion performance. As novel addition, we adapted the gain unit proposed for image compression to flexible-rate video compression in two ways: first, the gain unit enables a single encoder model to operate at multiple rate-distortion operating points; second, we exploit the gain unit to control bit allocation among intra-coded vs. bi-directionally coded frames by fine tuning corresponding models for truly flexible-rate learned video coding. Experimental results demonstrate that we obtain state-of-the-art rate-distortion performance exceeding those of all prior art in learned video coding.
Recent works have shown the ability of Implicit Neural Representations (INR) to carry meaningful representations of signal derivatives. In this work, we leverage this property to perform Video Frame Interpolation (VFI) by explicitly constraining the derivatives of the INR to satisfy the optical flow constraint equation. We achieve state of the art VFI on limited motion ranges using only a target video and its optical flow, without learning the interpolation operator from additional training data. We further show that constraining the INR derivatives not only allows to better interpolate intermediate frames but also improves the ability of narrow networks to fit the observed frames, which suggests potential applications to video compression and INR optimization.
The human eye cannot perceive small pixel changes in images or videos until a certain threshold of distortion. In the context of video compression, Just Noticeable Difference (JND) is the smallest distortion level from which the human eye can perceive the difference between reference video and the distorted/compressed one. Satisfied-User-Ratio (SUR) curve is the complementary cumulative distribution function of the individual JNDs of a viewer group. However, most of the previous works predict each point in SUR curve by using features both from source video and from compressed videos with assumption that the group-based JND annotations follow Gaussian distribution, which is neither practical nor accurate. In this work, we firstly compared various common functions for SUR curve modeling. Afterwards, we proposed a novel parameter-driven method to predict the video-wise SUR from video features. Besides, we compared the prediction results of source-only features based (SRC-based) models and source plus compressed videos features (SRC+PVS-based) models.
We show how transformers can be used to vastly simplify neural video compression. Previous methods have been relying on an increasing number of architectural biases and priors, including motion prediction and warping operations, resulting in complex models. Instead, we independently map input frames to representations and use a transformer to model their dependencies, letting it predict the distribution of future representations given the past. The resulting video compression transformer outperforms previous methods on standard video compression data sets. Experiments on synthetic data show that our model learns to handle complex motion patterns such as panning, blurring and fading purely from data. Our approach is easy to implement, and we release code to facilitate future research.
The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H.264/H.265 for both motion and residual compression. In this work, we first propose a coarse-to-fine (C2F) deep video compression framework for better motion compensation, in which we perform motion estimation, compression and compensation twice in a coarse to fine manner. Our C2F framework can achieve better motion compensation results without significantly increasing bit costs. Observing hyperprior information (i.e., the mean and variance values) from the hyperprior networks contains discriminant statistical information of different patches, we also propose two efficient hyperprior-guided mode prediction methods. Specifically, using hyperprior information as the input, we propose two mode prediction networks to respectively predict the optimal block resolutions for better motion coding and decide whether to skip residual information from each block for better residual coding without introducing additional bit cost while bringing negligible extra computation cost. Comprehensive experimental results demonstrate our proposed C2F video compression framework equipped with the new hyperprior-guided mode prediction methods achieves the state-of-the-art performance on HEVC, UVG and MCL-JCV datasets.
Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands. In addition, models are usually optimized for a single RD tradeoff. Recent slimmable image codecs can dynamically adjust their model capacity to gracefully reduce the memory and computation requirements, without harming RD performance. In this paper we propose a slimmable video codec (SlimVC), by integrating a slimmable temporal entropy model in a slimmable autoencoder. Despite a significantly more complex architecture, we show that slimming remains a powerful mechanism to control rate, memory footprint, computational cost and latency, all being important requirements for practical video compression.
Human perception is at the core of lossy video compression and yet, it is challenging to collect data that is sufficiently dense to drive compression. In perceptual quality assessment, human feedback is typically collected as a single scalar quality score indicating preference of one distorted video over another. In reality, some videos may be better in some parts but not in others. We propose an approach to collecting finer-grained feedback by asking users to use an interactive tool to directly optimize for perceptual quality given a fixed bitrate. To this end, we built a novel web-tool which allows users to paint these spatio-temporal importance maps over videos. The tool allows for interactive successive refinement: we iteratively re-encode the original video according to the painted importance maps, while maintaining the same bitrate, thus allowing the user to visually see the trade-off of assigning higher importance to one spatio-temporal part of the video at the cost of others. We use this tool to collect data in-the-wild (10 videos, 17 users) and utilize the obtained importance maps in the context of x264 coding to demonstrate that the tool can indeed be used to generate videos which, at the same bitrate, look perceptually better through a subjective study - and are 1.9 times more likely to be preferred by viewers. The code for the tool and dataset can be found at https://github.com/jenyap/video-annotation-tool.git
We consider the image and video compression on resource limited platforms. An ultra low-cost image encoder, named Block Modulating Video Compression (BMVC) with an encoding complexity ${\cal O}(1)$ is proposed to be implemented on mobile platforms with low consumption of power and computation resources. We also develop two types of BMVC decoders, implemented by deep neural networks. The first BMVC decoder is based on the Plug-and-Play (PnP) algorithm, which is flexible to different compression ratios. And the second decoder is a memory efficient end-to-end convolutional neural network, which aims for real-time decoding. Extensive results on the high definition images and videos demonstrate the superior performance of the proposed codec and the robustness against bit quantization.
The majority of internet traffic is video content. This drives the demand for video compression to deliver high quality video at low target bitrates. Optimising the parameters of a video codec for a specific video clip (per-clip optimisation) has been shown to yield significant bitrate savings. In previous work we have shown that per-clip optimisation of the Lagrangian multiplier leads to up to 24% BD-Rate improvement. A key component of these algorithms is modeling the R-D characteristic across the appropriate bitrate range. This is computationally heavy as it usually involves repeated video encodes of the high resolution material at different parameter settings. This work focuses on reducing this computational load by deploying a NN operating on lower bandwidth features. Our system achieves BD-Rate improvement in approximately 90% of a large corpus with comparable results to previous work in direct optimisation.
The majority of internet traffic is video content. This drives the demand for video compression in order to deliver high quality video at low target bitrates. This paper investigates the impact of adjusting the rate distortion equation on compression performance. An constant of proportionality, k, is used to modify the Lagrange multiplier used in H.265 (HEVC). Direct optimisation methods are deployed to maximise BD-Rate improvement for a particular clip. This leads to up to 21% BD-Rate improvement for an individual clip. Furthermore we use a more realistic corpus of material provided by YouTube. The results show that direct optimisation using BD-rate as the objective function can lead to further gains in bitrate savings that are not available with previous approaches.
Video conferencing has become a popular mode of meeting even if it consumes considerable communication resources. Conventional video compression causes resolution reduction under limited bandwidth. Semantic video conferencing maintains high resolution by transmitting some keypoints to represent motions because the background is almost static, and the speakers do not change often. However, the study on the impact of the transmission errors on keypoints is limited. In this paper, we initially establish a basal semantic video conferencing (SVC) network, which dramatically reduces transmission resources while only losing detailed expressions. The transmission errors in SVC only lead to a changed expression, whereas those in the conventional methods destroy pixels directly. However, the conventional error detector, such as the cyclic redundancy check, cannot reflect the degree of expression changes. To overcome this issue, we develop an incremental redundancy hybrid automatic repeat-request (IR-HARQ) framework for the varying channels (SVC-HARQ) incorporating a novel semantic error detector. The SVC-HARQ has flexibility in bit consumption and achieves good performance. In addition, SVC-CSI is designed for channel state information (CSI) feedback to allocate the keypoint transmission and enhance the performance dramatically. Simulation shows that the proposed wireless semantic communication system can significantly improve the transmission efficiency.This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
SVD (singular value decomposition) is one of the basic tools of machine learning, allowing to optimize basis for a given matrix. However, sometimes we have a set of matrices $\{A_k\}_k$ instead, and would like to optimize a single common basis for them: find orthogonal matrices $U$, $V$, such that $\{U^T A_k V\}$ set of matrices is somehow simpler. For example DCT-II is orthonormal basis of functions commonly used in image/video compression - as discussed here, this kind of basis can be quickly automatically optimized for a given dataset. While also discussed gradient descent optimization might be computationally costly, there is proposed CSVD (common SVD): fast general approach based on SVD. Specifically, we choose $U$ as built of eigenvectors of $\sum_i (w_k)^q (A_k A_k^T)^p$ and $V$ of $\sum_k (w_k)^q (A_k^T A_k)^p$, where $w_k$ are their weights, $p,q>0$ are some chosen powers e.g. 1/2, optionally with normalization e.g. $A \to A - rc^T$ where $r_i=\sum_j A_{ij}, c_j =\sum_i A_{ij}$.
The requirements of much larger file sizes, different storage formats, and immersive viewing conditions of VR pose significant challenges to the goals of acquiring, transmitting, compressing, and displaying high-quality VR content. At the same time, the great potential of deep learning to advance progress on the video compression problem has driven a significant research effort. Because of the high bandwidth requirements of VR, there has also been significant interest in the use of space-variant, foveated compression protocols. We have integrated these techniques to create an end-to-end deep learning video compression framework. A feature of our new compression model is that it dispenses with the need for expensive search-based motion prediction computations. This is accomplished by exploiting statistical regularities inherent in video motion expressed by displaced frame differences. Foveation protocols are desirable since only a small portion of a video viewed in VR may be visible as a user gazes in any given direction. Moreover, even within a current field of view (FOV), the resolution of retinal neurons rapidly decreases with distance (eccentricity) from the projected point of gaze. In our learning based approach, we implement foveation by introducing a Foveation Generator Unit (FGU) that generates foveation masks which direct the allocation of bits, significantly increasing compression efficiency while making it possible to retain an impression of little to no additional visual loss given an appropriate viewing geometry. Our experiment results reveal that our new compression model, which we call the Foveated MOtionless VIdeo Codec (Foveated MOVI-Codec), is able to efficiently compress videos without computing motion, while outperforming foveated version of both H.264 and H.265 on the widely used UVG dataset and on the HEVC Standard Class B Test Sequences.
Recent advances in deep generative models led to the development of neural face video compression codecs that use an order of magnitude less bandwidth than engineered codecs. These neural codecs reconstruct the current frame by warping a source frame and using a generative model to compensate for imperfections in the warped source frame. Thereby, the warp is encoded and transmitted using a small number of keypoints rather than a dense flow field, which leads to massive savings compared to traditional codecs. However, by relying on a single source frame only, these methods lead to inaccurate reconstructions (e.g. one side of the head becomes unoccluded when turning the head and has to be synthesized). Here, we aim to tackle this issue by relying on multiple source frames (views of the face) and present encouraging results.
Learned image compression research has achieved state-of-the-art compression performance with auto-encoder based neural network architectures, where the image is mapped via convolutional neural networks (CNN) into a latent representation that is quantized and processed again with CNN to obtain the reconstructed image. CNN operate on entire input images. On the other hand, traditional state-of-the-art image and video compression methods process images with a block-by-block processing approach for various reasons. Very recently, work on learned image compression with block based approaches have also appeared, which use the auto-encoder architecture on large blocks of the input image and introduce additional neural networks that perform intra/spatial prediction and deblocking/post-processing functions. This paper explores an alternative learned block-based image compression approach in which neither an explicit intra prediction neural network nor an explicit deblocking neural network is used. A single auto-encoder neural network with block-level masked convolutions is used and the block size is much smaller (8x8). By using block-level masked convolutions, each block is processed using reconstructed neighboring left and upper blocks both at the encoder and decoder. Hence, the mutual information between adjacent blocks is exploited during compression and each block is reconstructed using neighboring blocks, resolving the need for explicit intra prediction and deblocking neural networks. Since the explored system is a closed loop system, a special optimization procedure, the asymptotic closed loop design, is used with standard stochastic gradient descent based training. The experimental results indicate competitive image compression performance.
Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial attacks on deep learning-based video compression and downstream classification systems. Our attack framework, dubbed RoVISQ, manipulates the Rate-Distortion ($\textit{R}$-$\textit{D}$) relationship of a video compression model to achieve one or both of the following goals: (1) increasing the network bandwidth, (2) degrading the video quality for end-users. We further devise new objectives for targeted and untargeted attacks to a downstream video classification service. Finally, we design an input-invariant perturbation that universally disrupts video compression and classification systems in real time. Unlike previously proposed attacks on video classification, our adversarial perturbations are the first to withstand compression. We empirically show the resilience of RoVISQ attacks against various defenses, i.e., adversarial training, video denoising, and JPEG compression. Our extensive experimental results on various video datasets show RoVISQ attacks deteriorate peak signal-to-noise ratio by up to 5.6dB and the bit-rate by up to $\sim$ 2.4$\times$ while achieving over 90$\%$ attack success rate on a downstream classifier. Our user study further demonstrates the effect of RoVISQ attacks on users' QoE.