Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in perceptual and probabilistic forecasting metrics. We propose an autoregressive, end-to-end optimized video diffusion model inspired by recent advances in neural video compression. The model successively generates future frames by correcting a deterministic next-frame prediction using a stochastic residual generated by an inverse diffusion process. We compare this approach against five baselines on four datasets involving natural and simulation-based videos. We find significant improvements in terms of perceptual quality for all datasets. Furthermore, by introducing a scalable version of the Continuous Ranked Probability Score (CRPS) applicable to video, we show that our model also outperforms existing approaches in their probabilistic frame forecasting ability.
Humans do not perceive all parts of a scene with the same resolution, but rather focus on few regions of interest (ROIs). Traditional Object-Based codecs take advantage of this biological intuition, and are capable of non-uniform allocation of bits in favor of salient regions, at the expense of increased distortion the remaining areas: such a strategy allows a boost in perceptual quality under low rate constraints. Recently, several neural codecs have been introduced for video compression, yet they operate uniformly over all spatial locations, lacking the capability of ROI-based processing. In this paper, we introduce two models for ROI-based neural video coding. First, we propose an implicit model that is fed with a binary ROI mask and it is trained by de-emphasizing the distortion of the background. Secondly, we design an explicit latent scaling method, that allows control over the quantization binwidth for different spatial regions of latent variables, conditioned on the ROI mask. By extensive experiments, we show that our methods outperform all our baselines in terms of Rate-Distortion (R-D) performance in the ROI. Moreover, they can generalize to different datasets and to any arbitrary ROI at inference time. Finally, they do not require expensive pixel-level annotations during training, as synthetic ROI masks can be used with little to no degradation in performance. To the best of our knowledge, our proposals are the first solutions that integrate ROI-based capabilities into neural video compression models.
This paper presents a method to accurately estimate the required decoding energy for a given HEVC software decoding solution. We show that the decoder's processing time as returned by common C++ and UNIX functions is a highly suitable parameter to obtain valid estimations for the actual decoding energy. We verify this hypothesis by performing an exhaustive measurement series using different decoder setups and video bit streams. Our findings can be used by developers and researchers in the search for new energy saving video compression algorithms.
For 20 years, the gold standard to evaluate the performance of video codecs is to calculate average differences between ratedistortion curves, also called the "Bj{\o}ntegaard Delta". With the help of this tool, the compression performance of codecs can be compared. In the past years, we could observe that the calculus was also deployed for other metrics than bitrate and distortion in terms of peak signal-to-noise ratio, for example other quality metrics such as video multi-method assessment fusion or hardware-dependent metrics such as the decoding energy. However, it is unclear whether the Bj{\o}ntegaard Delta is a valid way to evaluate these metrics. To this end, this paper reviews several interpolation methods and evaluates their accuracy using different performancemetrics. As a result, we propose to use a novel approach based on Akima interpolation, which returns the most accurate results for a large variety of performance metrics. The approximation accuracy of this new method is determined to be below a bound of 1.5%.
There are many tasks within video compression which require fast bit rate estimation. As an example, rate-control algorithms are only feasible because it is possible to estimate the required bit rate without needing to encode the entire block. With residual coding technology becoming more and more sophisticated, the corresponding bit rate models require more advanced features. In this work, we propose a set of four features together with a linear model, which is able to estimate the rate of arbitrary residual blocks which were compressed using the VVC standard. Our method outperforms other methods which were used for the same task both in terms of mean absolute error and mean relative error. Our model deviates by less than 4 bit on average over a large dataset of natural images.
Video streaming usage has seen a significant rise as entertainment, education, and business increasingly rely on online video. Optimizing video compression has the potential to increase access and quality of content to users, and reduce energy use and costs overall. In this paper, we present an application of the MuZero algorithm to the challenge of video compression. Specifically, we target the problem of learning a rate control policy to select the quantization parameters (QP) in the encoding process of libvpx, an open source VP9 video compression library widely used by popular video-on-demand (VOD) services. We treat this as a sequential decision making problem to maximize the video quality with an episodic constraint imposed by the target bitrate. Notably, we introduce a novel self-competition based reward mechanism to solve constrained RL with variable constraint satisfaction difficulty, which is challenging for existing constrained RL methods. We demonstrate that the MuZero-based rate control achieves an average 6.28% reduction in size of the compressed videos for the same delivered video quality level (measured as PSNR BD-rate) compared to libvpx's two-pass VBR rate control policy, while having better constraint satisfaction behavior.
Motion estimation and motion compensation are indispensable parts of inter prediction in video coding. Since the motion vector of objects is mostly in fractional pixel units, original reference pictures may not accurately provide a suitable reference for motion compensation. In this paper, we propose a deep reference picture generator which can create a picture that is more relevant to the current encoding frame, thereby further reducing temporal redundancy and improving video compression efficiency. Inspired by the recent progress of Convolutional Neural Network(CNN), this paper proposes to use a dilated CNN to build the generator. Moreover, we insert the generated deep picture into Versatile Video Coding(VVC) as a reference picture and perform a comprehensive set of experiments to evaluate the effectiveness of our network on the latest VVC Test Model VTM. The experimental results demonstrate that our proposed method achieves on average 9.7% bit saving compared with VVC under low-delay P configuration.
Video compression is indispensable to most video analysis systems. Despite saving transportation bandwidth, it also deteriorates downstream video understanding tasks, especially at low-bitrate settings. To systematically investigate this problem, we first thoroughly review the previous methods, revealing that three principles, i.e., task-decoupled, label-free, and data-emerged semantic prior, are critical to a machine-friendly coding framework but are not fully satisfied so far. In this paper, we propose a traditional-neural mixed coding framework that simultaneously fulfills all these principles, by taking advantage of both traditional codecs and neural networks (NNs). On one hand, the traditional codecs can efficiently encode the pixel signal of videos but may distort the semantic information. On the other hand, highly non-linear NNs are proficient in condensing video semantics into a compact representation. The framework is optimized by ensuring that a transportation-efficient semantic representation of the video is preserved w.r.t. the coding procedure, which is spontaneously learned from unlabeled data in a self-supervised manner. The videos collaboratively decoded from two streams (codec and NN) are of rich semantics, as well as visually photo-realistic, empirically boosting several mainstream downstream video analysis task performances without any post-adaptation procedure. Furthermore, by introducing the attention mechanism and adaptive modeling scheme, the video semantic modeling ability of our approach is further enhanced. Finally, we build a low-bitrate video understanding benchmark with three downstream tasks on eight datasets, demonstrating the notable superiority of our approach. All codes, data, and models will be available at \url{https://github.com/tianyuan168326/VCS-Pytorch}.
Everyone "knows" that compressing a video will degrade the accuracy of object tracking. Yet, a literature search on this topic reveals that there is very little documented evidence for this presumed fact. Part of the reason is that, until recently, there were no object tracking datasets for uncompressed video, which made studying the effects of compression on tracking accuracy difficult. In this paper, using a recently published dataset that contains tracking annotations for uncompressed videos, we examined the degradation of tracking accuracy due to video compression using rigorous statistical methods. Specifically, we examined the impact of quantization parameter (QP) and motion search range (MSR) on Multiple Object Tracking Accuracy (MOTA). The results show that QP impacts MOTA at the 95% confidence level, while there is insufficient evidence to claim that MSR impacts MOTA. Moreover, regression analysis allows us to derive a quantitative relationship between MOTA and QP for the specific tracker used in the experiments.
Video compression is a central feature of the modern internet powering technologies from social media to video conferencing. While video compression continues to mature, for many compression settings, quality loss is still noticeable. These settings nevertheless have important applications to the efficient transmission of videos over bandwidth constrained or otherwise unstable connections. In this work, we develop a deep learning architecture capable of restoring detail to compressed videos which leverages the underlying structure and motion information embedded in the video bitstream. We show that this improves restoration accuracy compared to prior compression correction methods and is competitive when compared with recent deep-learning-based video compression methods on rate-distortion while achieving higher throughput. Furthermore, we condition our model on quantization data which is readily available in the bitstream. This allows our single model to handle a variety of different compression quality settings which required an ensemble of models in prior work.
The rapid development of multimedia and communication technology has resulted in an urgent need for high-quality video streaming. However, robust video streaming under fluctuating network conditions and heterogeneous client computing capabilities remains a challenge. In this paper, we consider an enhancement-enabled video streaming network under a time-varying wireless network and limited computation capacity. "Enhancement" means that the client can improve the quality of the downloaded video segments via image processing modules. We aim to design a joint bitrate adaptation and client-side enhancement algorithm toward maximizing the quality of experience (QoE). We formulate the problem as a Markov decision process (MDP) and propose a deep reinforcement learning (DRL)-based framework, named ENAVS. As video streaming quality is mainly affected by video compression, we demonstrate that the video enhancement algorithm outperforms the super-resolution algorithm in terms of signal-to-noise ratio and frames per second, suggesting a better solution for client processing in video streaming. Ultimately, we implement ENAVS and demonstrate extensive testbed results under real-world bandwidth traces and videos. The simulation shows that ENAVS is capable of delivering 5%-14% more QoE under the same bandwidth and computing power conditions as conventional ABR streaming.
Neural fields have emerged as a powerful paradigm for representing various signals, including videos. However, research on improving the parameter efficiency of neural fields is still in its early stages. Even though neural fields that map coordinates to colors can be used to encode video signals, this scheme does not exploit the spatial and temporal redundancy of video signals. Inspired by standard video compression algorithms, we propose a neural field architecture for representing and compressing videos that deliberately removes data redundancy through the use of motion information across video frames. Maintaining motion information, which is typically smoother and less complex than color signals, requires a far fewer number of parameters. Furthermore, reusing color values through motion information further improves the network parameter efficiency. In addition, we suggest using more than one reference frame for video frame reconstruction and separate networks, one for optical flows and the other for residuals. Experimental results have shown that the proposed method outperforms the baseline methods by a significant margin. The code is available in https://github.com/daniel03c1/eff_video_representation
Recently, significant progress has been made in learned image and video compression. In particular the usage of Generative Adversarial Networks has lead to impressive results in the low bit rate regime. However, the model size remains an important issue in current state-of-the-art proposals and existing solutions require significant computation effort on the decoding side. This limits their usage in realistic scenarios and the extension to video compression. In this paper, we demonstrate how to leverage knowledge distillation to obtain equally capable image decoders at a fraction of the original number of parameters. We investigate several aspects of our solution including sequence specialization with side information for image coding. Finally, we also show how to transfer the obtained benefits into the setting of video compression. Overall, this allows us to reduce the model size by a factor of 20 and to achieve 50% reduction in decoding time.
Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained image compression. Most frameworks contain static compression and decompression models which are fixed after training, so efficient rate-distortion optimization is not possible. In a previous work, we proposed RDONet, which enables an RDO approach comparable to adaptive block partitioning in HEVC. In this paper, we enhance the training by introducing low-complexity estimations of the RDO result into the training. Additionally, we propose fast and very fast RDO inference modes. With our novel training method, we achieve average rate savings of 19.6% in MS-SSIM over the previous RDONet model, which equals rate savings of 27.3% over a comparable conventional deep image coder.
Conventional video compression (VC) methods are based on motion compensated transform coding, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to the combinatorial nature of the end-to-end optimization problem. Learned VC allows end-to-end rate-distortion (R-D) optimized training of nonlinear transform, motion and entropy model simultaneously. Most works on learned VC consider end-to-end optimization of a sequential video codec based on R-D loss averaged over pairs of successive frames. It is well-known in conventional VC that hierarchical, bi-directional coding outperforms sequential compression because of its ability to use both past and future reference frames. This paper proposes a learned hierarchical bi-directional video codec (LHBDC) that combines the benefits of hierarchical motion-compensated prediction and end-to-end optimization. Experimental results show that we achieve the best R-D results that are reported for learned VC schemes to date in both PSNR and MS-SSIM. Compared to conventional video codecs, the R-D performance of our end-to-end optimized codec outperforms those of both x265 and SVT-HEVC encoders ("veryslow" preset) in PSNR and MS-SSIM as well as HM 16.23 reference software in MS-SSIM. We present ablation studies showing performance gains due to proposed novel tools such as learned masking, flow-field subsampling, and temporal flow vector prediction. The models and instructions to reproduce our results can be found in https://github.com/makinyilmaz/LHBDC/
Motion compensated inter prediction is a common component of all video coders. The concept was established in traditional hybrid coding and successfully transferred to learning-based video compression. To compress the residual signal after prediction, usually the difference of the two signals is compressed using a standard autoencoder. However, information theory tells us that a general conditional coder is more efficient. In this paper, we provide a solid foundation based on information theory and Shannon entropy to show the potentials but also the limits of conditional coding. Building on those results, we then propose the generalized difference coder, a special case of a conditional coder designed to avoid limiting bottlenecks. With this coder, we are able to achieve average rate savings of 27.8% compared to a standard autoencoder, by only adding a moderate complexity overhead of less than 7%.
We present a dataset that contains object annotations with unique object identities (IDs) for the High Efficiency Video Coding (HEVC) v1 Common Test Conditions (CTC) sequences. Ground-truth annotations for 13 sequences were prepared and released as the dataset called SFU-HW-Tracks-v1. For each video frame, ground truth annotations include object class ID, object ID, and bounding box location and its dimensions. The dataset can be used to evaluate object tracking performance on uncompressed video sequences and study the relationship between video compression and object tracking.
Neural video codecs have demonstrated great potential in video transmission and storage applications. Existing neural hybrid video coding approaches rely on optical flow or Gaussian-scale flow for prediction, which cannot support fine-grained adaptation to diverse motion content. Towards more content-adaptive prediction, we propose a novel cross-scale prediction module that achieves more effective motion compensation. Specifically, on the one hand, we produce a reference feature pyramid as prediction sources and then transmit cross-scale flows that leverage the feature scale to control the precision of prediction. On the other hand, for the first time, a weighted prediction mechanism is introduced even if only a single reference frame is available, which can help synthesize a fine prediction result by transmitting cross-scale weight maps. In addition to the cross-scale prediction module, we further propose a multi-stage quantization strategy, which improves the rate-distortion performance with no extra computational penalty during inference. We show the encouraging performance of our efficient neural video codec (ENVC) on several benchmark datasets. In particular, the proposed ENVC can compete with the latest coding standard H.266/VVC in terms of sRGB PSNR on UVG dataset for the low-latency mode. We also analyze in detail the effectiveness of the cross-scale prediction module in handling various video content, and provide a comprehensive ablation study to analyze those important components. Test code is available at https://github.com/USTC-IMCL/ENVC .
A variety of compression methods based on encoding images as weights of a neural network have been recently proposed. Yet, the potential of similar approaches for video compression remains unexplored. In this work, we suggest a set of experiments for testing the feasibility of compressing video using two architectural paradigms, coordinate-based MLP (CbMLP) and convolutional network. Furthermore, we propose a novel technique of neural weight stepping, where subsequent frames of a video are encoded as low-entropy parameter updates. To assess the feasibility of the considered approaches, we will test the video compression performance on several high-resolution video datasets and compare against existing conventional and neural compression techniques.
This paper presents a deep learning-based video compression framework (ViSTRA3). The proposed framework intelligently adapts video format parameters of the input video before encoding, subsequently employing a CNN at the decoder to restore their original format and enhance reconstruction quality. ViSTRA3 has been integrated with the H.266/VVC Test Model VTM 14.0, and evaluated under the Joint Video Exploration Team Common Test Conditions. Bj{\o}negaard Delta (BD) measurement results show that the proposed framework consistently outperforms the original VVC VTM, with average BD-rate savings of 1.8% and 3.7% based on the assessment of PSNR and VMAF.