The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully exploit the temporal correlation among video frames. To overcome this shortcoming, this paper proposes a Recurrent Learned Video Compression (RLVC) approach with the Recurrent Auto-Encoder (RAE) and Recurrent Probability Model (RPM). Specifically, the RAE employs recurrent cells in both the encoder and decoder. As such, the temporal information in a large range of frames can be used for generating latent representations and reconstructing compressed outputs. Furthermore, the proposed RPM network recurrently estimates the Probability Mass Function (PMF) of the latent representation, conditioned on the distribution of previous latent representations. Due to the correlation among consecutive frames, the conditional cross entropy can be lower than the independent cross entropy, thus reducing the bit-rate. The experiments show that our approach achieves the state-of-the-art learned video compression performance in terms of both PSNR and MS-SSIM. Moreover, our approach outperforms the default Low-Delay P (LDP) setting of x265 on PSNR, and also has better performance on MS-SSIM than the SSIM-tuned x265 and the slowest setting of x265. The codes are available at https://github.com/RenYang-home/RLVC.git.
In typical point cloud delivery, a sender uses octree-based digital video compression to send three-dimensional (3D) points and color attributes over band-limited links. However, the digital-based schemes have an issue called the cliff effect, where the 3D reconstruction quality will be a step function in terms of wireless channel quality. To prevent the cliff effect subject to channel quality fluctuation, we have proposed soft point cloud delivery called HoloCast. Although the HoloCast realizes graceful quality improvement according to wireless channel quality, it requires large communication overheads. In this paper, we propose a novel scheme for soft point cloud delivery to simultaneously realize better quality and lower communication overheads. The proposed scheme introduces an end-to-end deep learning framework based on graph neural network (GNN) to reconstruct high-quality point clouds from its distorted observation under wireless fading channels. We demonstrate that the proposed GNN-based scheme can reconstruct clean 3D point cloud with low overheads by removing fading and noise effects.
Speech as a natural signal is composed of three parts - visemes (visual part of speech), phonemes (spoken part of speech), and language (the imposed structure). However, video as a medium for the delivery of speech and a multimedia construct has mostly ignored the cognitive aspects of speech delivery. For example, video applications like transcoding and compression have till now ignored the fact how speech is delivered and heard. To close the gap between speech understanding and multimedia video applications, in this paper, we show the initial experiments by modelling the perception on visual speech and showing its use case on video compression. On the other hand, in the visual speech recognition domain, existing studies have mostly modeled it as a classification problem, while ignoring the correlations between views, phonemes, visemes, and speech perception. This results in solutions which are further away from how human perception works. To bridge this gap, we propose a view-temporal attention mechanism to model both the view dependence and the visemic importance in speech recognition and understanding. We conduct experiments on three public visual speech recognition datasets. The experimental results show that our proposed method outperformed the existing work by 4.99% in terms of the viseme error rate. Moreover, we show that there is a strong correlation between our model's understanding of multi-view speech and the human perception. This characteristic benefits downstream applications such as video compression and streaming where a significant number of less important frames can be compressed or eliminated while being able to maximally preserve human speech understanding with good user experience.
Moving object detection is critical for automated video analysis in many vision-related tasks, such as surveillance tracking, video compression coding, etc. Robust Principal Component Analysis (RPCA), as one of the most popular moving object modelling methods, aims to separate the temporally varying (i.e., moving) foreground objects from the static background in video, assuming the background frames to be low-rank while the foreground to be spatially sparse. Classic RPCA imposes sparsity of the foreground component using l1-norm, and minimizes the modeling error via 2-norm. We show that such assumptions can be too restrictive in practice, which limits the effectiveness of the classic RPCA, especially when processing videos with dynamic background, camera jitter, camouflaged moving object, etc. In this paper, we propose a novel RPCA-based model, called Hyper RPCA, to detect moving objects on the fly. Different from classic RPCA, the proposed Hyper RPCA jointly applies the maximum correntropy criterion (MCC) for the modeling error, and Laplacian scale mixture (LSM) model for foreground objects. Extensive experiments have been conducted, and the results demonstrate that the proposed Hyper RPCA has competitive performance for foreground detection to the state-of-the-art algorithms on several well-known benchmark datasets.
Deep learning has shown great potential in image and video compression tasks. However, it brings bit savings at the cost of significant increases in coding complexity, which limits its potential for implementation within practical applications. In this paper, a novel neural network-based tool is presented which improves the interpolation of reference samples needed for fractional precision motion compensation. Contrary to previous efforts, the proposed approach focuses on complexity reduction achieved by interpreting the interpolation filters learned by the networks. When the approach is implemented in the Versatile Video Coding (VVC) test model, up to 4.5% BD-rate saving for individual sequences is achieved compared with the baseline VVC, while the complexity of learned interpolation is significantly reduced compared to the application of full neural network.
We present an end-to-end trainable framework for P-frame compression in this paper. A joint motion vector (MV) and residual prediction network MV-Residual is designed to extract the ensembled features of motion representations and residual information by treating the two successive frames as inputs. The prior probability of the latent representations is modeled by a hyperprior autoencoder and trained jointly with the MV-Residual network. Specially, the spatially-displaced convolution is applied for video frame prediction, in which a motion kernel for each pixel is learned to generate predicted pixel by applying the kernel at a displaced location in the source image. Finally, novel rate allocation and post-processing strategies are used to produce the final compressed bits, considering the bits constraint of the challenge. The experimental results on validation set show that the proposed optimized framework can generate the highest MS-SSIM for P-frame compression competition.
Although CNN has reached satisfactory performance in image-related tasks, using CNN to process videos is much more challenging due to the enormous size of raw video streams. In this work, we propose to use motion vectors and residuals from modern video compression techniques to effectively learn the representation of the raw frames and greatly remove the temporal redundancy, giving a faster video processing model. Compressed Video Action Recognition(CoViAR) has explored to directly use compressed video to train the deep neural network, where the motion vectors were utilized to present temporal information. However, motion vector is designed for minimizing video size where precise motion information is not obligatory. Compared with optical flow, motion vectors contain noisy and unreliable motion information. Inspired by the mechanism of video compression codecs, we propose an approach to refine the motion vectors where unreliable movement will be removed while temporal information is largely reserved. We prove that replacing the original motion vector with refined one and using the same network as CoViAR has achieved state-of-art performance on the UCF-101 and HMDB-51 with negligible efficiency degrades comparing with original CoViAR.
We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures. To compress the TSDF, our method relies on a block-based neural network architecture trained end-to-end, achieving state-of-the-art rate-distortion trade-off. To prevent topological errors, we losslessly compress the signs of the TSDF, which also upper bounds the reconstruction error by the voxel size. To compress the corresponding texture, we designed a fast block-based UV parameterization, generating coherent texture maps that can be effectively compressed using existing video compression algorithms. We demonstrate the performance of our algorithms on two 4D performance capture datasets, reducing bitrate by 66% for the same distortion, or alternatively reducing the distortion by 50% for the same bitrate, compared to the state-of-the-art.
With several advantages over conventional RGB cameras, event cameras have provided new opportunities for tackling visual tasks under challenging scenarios with fast motion, high dynamic range, and/or power constraint. Yet unlike image/video compression, the performance of event compression algorithm is far from satisfying and practical. The main challenge for compressing events is the unique event data form, i.e., a stream of asynchronously fired event tuples each encoding the 2D spatial location, timestamp, and polarity (denoting an increase or decrease in brightness). Since events only encode temporal variations, they lack spatial structure which is crucial for compression. To address this problem, we propose a novel event compression algorithm based on a quad tree (QT) segmentation map derived from the adjacent intensity images. The QT informs 2D spatial priority within the 3D space-time volume. In the event encoding step, events are first aggregated over time to form polarity-based event histograms. The histograms are then variably sampled via Poisson Disk Sampling prioritized by the QT based segmentation map. Next, differential encoding and run length encoding are employed for encoding the spatial and polarity information of the sampled events, respectively, followed by Huffman encoding to produce the final encoded events. Our Poisson Disk Sampling based Lossy Event Compression (PDS-LEC) algorithm performs rate-distortion based optimal allocation. On average, our algorithm achieves greater than 6x compression compared to the state of the art.
Remote Photoplethysmography (rPPG) is a fast-growing technique of vital sign estimation by analyzing video of a person. Several major phenomena affecting rPPG signals have been studied (e.g. video compression, distance from person to camera, skin tone, head motions). However, to develop a highly accurate rPPG method, new, minor, factors should be investigated. First considered factor is irregular frame rate of video recordings. Despite of PPG signal transformation by frame rate irregularity, no significant distortion of PPG signal spectra was found in the experiments. Second factor is rolling shutter effect which generates tiny phase shift of the same PPG signal in different parts of the frame caused by progressive scanning. In particular conditions effect of this artifact could be of the same order of magnitude as physiologically caused phase shifts. Third factor is a size of temporal windows, which could significantly influence the estimated error of vital sign evaluation. It follows that one should account difference in size of processing windows when comparing rPPG methods. Short series of experiments were conducted to estimate importance of these phenomena and to determine necessity of their further comprehensive study.
With the increasing demand for video content at higher resolutions, it is evermore critical to find ways to limit the complexity of video encoding tasks in order to reduce costs, power consumption and environmental impact of video services. In the last few years, algorithms based on Neural Networks (NN) have been shown to benefit many conventional video coding modules. But while such techniques can considerably improve the compression efficiency, they usually are very computationally intensive. It is highly beneficial to simplify models learnt by NN so that meaningful insights can be exploited with the goal of deriving less complex solutions. This paper presents two ways to derive simplified intra-prediction from learnt models, and shows that these streamlined techniques can lead to efficient compression solutions.
We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references. In our scheme, the motion vector (MV) field is calculated between the current frame and the previous one. With multiple reference frames and associated multiple MV fields, our designed network can generate more accurate prediction of the current frame, yielding less residual. Multiple reference frames also help generate MV prediction, which reduces the coding cost of MV field. We use two deep auto-encoders to compress the residual and the MV, respectively. To compensate for the compression error of the auto-encoders, we further design a MV refinement network and a residual refinement network, taking use of the multiple reference frames as well. All the modules in our scheme are jointly optimized through a single rate-distortion loss function. We use a step-by-step training strategy to optimize the entire scheme. Experimental results show that the proposed method outperforms the existing learned video compression methods for low-latency mode. Our method also performs better than H.265 in both PSNR and MS-SSIM. Our code and models are publicly available.
In this paper, we present a novel adversarial lossy video compression model. At extremely low bit-rates, standard video coding schemes suffer from unpleasant reconstruction artifacts such as blocking, ringing etc. Existing learned neural approaches to video compression have achieved reasonable success on reducing the bit-rate for efficient transmission and reduce the impact of artifacts to an extent. However, they still tend to produce blurred results under extreme compression. In this paper, we present a deep adversarial learned video compression model that minimizes an auxiliary adversarial distortion objective. We find this adversarial objective to correlate better with human perceptual quality judgement relative to traditional quality metrics such as MS-SSIM and PSNR. Our experiments using a state-of-the-art learned video compression system demonstrate a reduction of perceptual artifacts and reconstruction of detail lost especially under extremely high compression.
Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learned image or video compression solutions are emerging as strong competitors to traditional approaches. In this work, We propose a new network architecture, based on common and well studied components, for learned video compression operating in low latency mode. Our method yields state of the art MS-SSIM/rate performance on the high-resolution UVG dataset, among both learned video compression approaches and classical video compression methods (H.265 and H.264) in the rate range of interest for streaming applications. Additionally, we provide an analysis of existing approaches through the lens of their underlying probabilistic graphical models. Finally, we point out issues with temporal consistency and color shift observed in empirical evaluation, and suggest directions forward to alleviate those.
In recent years, neural network-based image compression techniques have been able to outperform traditional codecs and have opened the gates for the development of learning-based video codecs. However, to take advantage of the high temporal correlation in videos, more sophisticated architectures need to be employed. This paper presents PredEncoder, a hybrid video compression framework based on the concept of predictive auto-encoding that models the temporal correlations between consecutive video frames using a prediction network which is then combined with a progressive encoder network to exploit the spatial redundancies. A variable-rate block encoding scheme has been proposed in the paper that leads to remarkably high quality to bit-rate ratios. By joint training and fine-tuning of this hybrid architecture, PredEncoder has been able to gain significant improvement over the MPEG-4 codec and has achieved bit-rate savings over the H.264 codec in the low to medium bit-rate range for HD videos and comparable results over most bit-rates for non-HD videos. This paper serves to demonstrate how neural architectures can be leveraged to perform at par with the highly optimized traditional methodologies in the video compression domain.
Deep learning methods are increasingly being applied in the optimisation of video compression algorithms and can achieve significantly enhanced coding gains, compared to conventional approaches. Such approaches often employ Convolutional Neural Networks (CNNs) which are trained on databases with relatively limited content coverage. In this paper, a new extensive and representative video database, BVI-DVC, is presented for training CNN-based video compression systems, with specific emphasis on machine learning tools that enhance conventional coding architectures, including spatial resolution and bit depth up-sampling, post-processing and in-loop filtering. BVI-DVC contains 800 sequences at various spatial resolutions from 270p to 2160p and has been evaluated on ten existing network architectures for four different coding tools. Experimental results show that this database produces significant improvements in terms of coding gains over three existing (commonly used) image/video training databases under the same training and evaluation configurations. The overall additional coding improvements by using the proposed database for all tested coding modules and CNN architectures are up to 10.3% based on the assessment of PSNR and 8.1% based on VMAF.
Recently, learning based video compression methods attract increasing attention. However, the previous works suffer from error propagation due to the accumulation of reconstructed error in inter predictive coding. Meanwhile, the previous learning based video codecs are also not adaptive to different video contents. To address these two problems, we propose a content adaptive and error propagation aware video compression system. Specifically, our method employs a joint training strategy by considering the compression performance of multiple consecutive frames instead of a single frame. Based on the learned long-term temporal information, our approach effectively alleviates error propagation in reconstructed frames. More importantly, instead of using the hand-crafted coding modes in the traditional compression systems, we design an online encoder updating scheme in our system. The proposed approach updates the parameters for encoder according to the rate-distortion criterion but keeps the decoder unchanged in the inference stage. Therefore, the encoder is adaptive to different video contents and achieves better compression performance by reducing the domain gap between the training and testing datasets. Our method is simple yet effective and outperforms the state-of-the-art learning based video codecs on benchmark datasets without increasing the model size or decreasing the decoding speed.
Natural environment and our interaction with it is essentially multisensory, where we may deploy visual, tactile and/or auditory senses to perceive, learn and interact with our environment. Our objective in this study is to develop a scene analysis algorithm using multisensory information, specifically vision and audio. We develop a proto-object based audiovisual saliency map (AVSM) for the analysis of dynamic natural scenes. A specialized audiovisual camera with $360 \degree$ Field of View, capable of locating sound direction, is used to collect spatiotemporally aligned audiovisual data. We demonstrate that the performance of proto-object based audiovisual saliency map in detecting and localizing salient objects/events is in agreement with human judgment. In addition, the proto-object based AVSM that we compute as a linear combination of visual and auditory feature conspicuity maps captures a higher number of valid salient events compared to unisensory saliency maps. Such an algorithm can be useful in surveillance, robotic navigation, video compression and related applications.
In this paper, we propose a Hierarchical Learned Video Compression (HLVC) method with three hierarchical quality layers and a recurrent enhancement network. The frames in the first layer are compressed by an image compression method with the highest quality. Using these frames as references, we propose the Bi-Directional Deep Compression (BDDC) network to compress the second layer with relatively high quality. Then, the third layer frames are compressed with the lowest quality, by the proposed Single Motion Deep Compression (SMDC) network, which adopts a single motion map to estimate the motions of multiple frames, thus saving bits for motion information. In our deep decoder, we develop the Weighted Recurrent Quality Enhancement (WRQE) network, which takes both compressed frames and the bit stream as inputs. In the recurrent cell of WRQE, the memory and update signal are weighted by quality features to reasonably leverage multi-frame information for enhancement. In our HLVC approach, the hierarchical quality benefits the coding efficiency, since the high quality information facilitates the compression and enhancement of low quality frames at encoder and decoder sides, respectively. Finally, the experiments validate that our HLVC approach advances the state-of-the-art of deep video compression methods, and outperforms the "Low-Delay P (LDP) very fast" mode of x265 in terms of both PSNR and MS-SSIM. The project page is at https://github.com/RenYang-home/HLVC.
Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before. Manipulated videos can fuel disinformation and reduce trust in media. Therefore detection of fake videos has garnered immense interest in academia and industry. Recently developed Deepfake detection methods rely on deep neural networks (DNNs) to distinguish AI-generated fake videos from real videos. In this work, we demonstrate that it is possible to bypass such detectors by adversarially modifying fake videos synthesized using existing Deepfake generation methods. We further demonstrate that our adversarial perturbations are robust to image and video compression codecs, making them a real-world threat. We present pipelines in both white-box and black-box attack scenarios that can fool DNN based Deepfake detectors into classifying fake videos as real.