Light field (LF) imaging has gained significant attention due to its recent success in 3-dimensional (3D) displaying and rendering as well as augmented and virtual reality usage. Nonetheless, because of the two extra dimensions, LFs are much larger than conventional images. We develop a JPEG-assisted learning-based technique to reconstruct an LF from a JPEG bitstream with a bit per pixel ratio of 0.0047 on average. For compression, we keep the LF's center view and use JPEG compression with 50% quality. Our reconstruction pipeline consists of a small JPEG enhancement network (JPEG-Hance), a depth estimation network (Depth-Net), followed by view synthesizing by warping the enhanced center view. Our pipeline is significantly faster than using video compression on pseudo-sequences extracted from an LF, both in compression and decompression, while maintaining effective performance. We show that with a 1% compression time cost and 18x speedup for decompression, our methods reconstructed LFs have better structural similarity index metric (SSIM) and comparable peak signal-to-noise ratio (PSNR) compared to the state-of-the-art video compression techniques used to compress LFs.
With the development of higher resolution contents and displays, its significant volume poses significant challenges to the goals of acquiring, transmitting, compressing, and displaying high-quality video content. In this paper, we propose a new deep learning video compression architecture that does not require motion estimation, which is the most expensive element of modern hybrid video compression codecs like H.264 and HEVC. Our framework exploits the regularities inherent to video motion, which we capture by using displaced frame differences as video representations to train the neural network. In addition, we propose a new space-time reconstruction network based on both an LSTM model and a UNet model, which we call LSTM-UNet. The new video compression framework has three components: a Displacement Calculation Unit (DCU), a Displacement Compression Network (DCN), and a Frame Reconstruction Network (FRN). The DCU removes the need for motion estimation found in hybrid codecs and is less expensive. In the DCN, an RNN-based network is utilized to compress displaced frame differences as well as retain temporal information between frames. The LSTM-UNet is used in the FRN to learn space-time differential representations of videos. Our experimental results show that our compression model, which we call the MOtionless VIdeo Codec (MOVI-Codec), learns how to efficiently compress videos without computing motion. Our experiments show that MOVI-Codec outperforms the Low-Delay P veryfast setting of the video coding standard H.264 and exceeds the performance of the modern global standard HEVC codec, using the same setting, as measured by MS-SSIM, especially on higher resolution videos. In addition, our network outperforms the latest H.266 (VVC) codec at higher bitrates, when assessed using MS-SSIM, on high-resolution videos.
We introduce an open source Tensorflow implementation of the Deep Video Compression (DVC) method in this technical report. DVC is the first end-to-end optimized learned video compression method, achieving better MS-SSIM performance than the Low-Delay P (LDP) very fast setting of x265 and comparable PSNR performance with x265 (LDP very fast). At the time of writing this report, several learned video compression methods are superior to DVC, but currently none of them provides open source codes. We hope that our OpenDVC codes are able to provide a useful model for further development, and facilitate future researches on learned video compression. Different from the original DVC, which is only optimized for PSNR, we release not only the PSNR-optimized re-implementation, denoted by OpenDVC (PSNR), but also the MS-SSIM-optimized model OpenDVC (MS-SSIM). Our OpenDVC (MS-SSIM) model provides a more convincing baseline for MS-SSIM optimized methods, which can only compare with the PSNR optimized DVC in the past. The OpenDVC source codes and pre-trained models are publicly released at https://github.com/RenYang-home/OpenDVC.
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.
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.
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.
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 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.
Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation.However, existing methods still perform poorly on challenging video tasks such as long-term forecasting. This is because these kinds of challenging tasks require learning long-term spatio-temporal correlations in the video sequence. In this paper, we propose a higher-order convolutional LSTM model that can efficiently learn these correlations, along with a succinct representations of the history. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. To make this feasible in terms of computation and memory requirements, we propose a novel convolutional tensor-train decomposition of the higher-order model. This decomposition reduces the model complexity by jointly approximating a sequence of convolutional kernels asa low-rank tensor-train factorization. As a result, our model outperforms existing approaches, but uses only a fraction of parameters, including the baseline models.Our results achieve state-of-the-art performance in a wide range of applications and datasets, including the multi-steps video prediction on the Moving-MNIST-2and KTH action datasets as well as early activity recognition on the Something-Something V2 dataset.
Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks. However, the current state-of-the-art learning based image compression methods suffer from the huge computational cost, which limits their capacity for practical applications. In this paper, we propose a unified framework called Efficient Deep Image Compression (EDIC) based on three new technologies, including a channel attention module, a Gaussian mixture model and a decoder-side enhancement module. Specifically, we design an auto-encoder style network for learning based image compression. To improve the coding efficiency, we exploit the channel relationship between latent representations by using the channel attention module. Besides, the Gaussian mixture model is introduced for the entropy model and improves the accuracy for bitrate estimation. Furthermore, we introduce the decoder-side enhancement module to further improve image compression performance. Our EDIC method can also be readily incorporated with the Deep Video Compression (DVC) framework to further improve the video compression performance. Simultaneously, our EDIC method boosts the coding performance significantly while bringing slightly increased computational cost. More importantly, experimental results demonstrate that the proposed approach outperforms the current state-of-the-art image compression methods and is up to more than 150 times faster in terms of decoding speed when compared with Minnen's method. The proposed framework also successfully improves the performance of the recent deep video compression system DVC. Our code will be released at https://github.com/liujiaheng/compression.
Standard video codecs rely on optical flow to guide inter-frame prediction: pixels from reference frames are moved via motion vectors to predict target video frames. We propose to learn binary motion codes that are encoded based on an input video sequence. These codes are not limited to 2D translations, but can capture complex motion (warping, rotation and occlusion). Our motion codes are learned as part of a single neural network which also learns to compress and decode them. This approach supports parallel video frame decoding instead of the sequential motion estimation and compensation of flow-based methods. We also introduce 3D dynamic bit assignment to adapt to object displacements caused by motion, yielding additional bit savings. By replacing the optical flow-based block-motion algorithms found in an existing video codec with our learned inter-frame prediction model, our approach outperforms the standard H.264 and H.265 video codecs across at low bitrates.
Variable rate is a requirement for flexible and adaptable image and video compression. However, deep image compression methods are optimized for a single fixed rate-distortion tradeoff. While this can be addressed by training multiple models for different tradeoffs, the memory requirements increase proportionally to the number of models. Scaling the bottleneck representation of a shared autoencoder can provide variable rate compression with a single shared autoencoder. However, the R-D performance using this simple mechanism degrades in low bitrates, and also shrinks the effective range of bit rates. Addressing these limitations, we formulate the problem of variable rate-distortion optimization for deep image compression, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific rate-distortion tradeoff via a modulation network. Jointly training this modulated autoencoder and modulation network provides an effective way to navigate the R-D operational curve. Our experiments show that the proposed method can achieve almost the same R-D performance of independent models with significantly fewer parameters.
Remote photoplethysmography (rPPG), which aims at measuring heart activities without any contact, has great potential in many applications (e.g., remote healthcare). Existing rPPG approaches rely on analyzing very fine details of facial videos, which are prone to be affected by video compression. Here we propose a two-stage, end-to-end method using hidden rPPG information enhancement and attention networks, which is the first attempt to counter video compression loss and recover rPPG signals from highly compressed videos. The method includes two parts: 1) a Spatio-Temporal Video Enhancement Network (STVEN) for video enhancement, and 2) an rPPG network (rPPGNet) for rPPG signal recovery. The rPPGNet can work on its own for robust rPPG measurement, and the STVEN network can be added and jointly trained to further boost the performance especially on highly compressed videos. Comprehensive experiments are performed on two benchmark datasets to show that, 1) the proposed method not only achieves superior performance on compressed videos with high-quality videos pair, 2) it also generalizes well on novel data with only compressed videos available, which implies the promising potential for real world applications.
The field of video compression has developed some of the most sophisticated and efficient compression algorithms known in the literature, enabling very high compressibility for little loss of information. Whilst some of these techniques are domain specific, many of their underlying principles are universal in that they can be adapted and applied for compressing different types of data. In this work we present DeepCABAC, a compression algorithm for deep neural networks that is based on one of the state-of-the-art video coding techniques. Concretely, it applies a Context-based Adaptive Binary Arithmetic Coder (CABAC) to the network's parameters, which was originally designed for the H.264/AVC video coding standard and became the state-of-the-art for lossless compression. Moreover, DeepCABAC employs a novel quantization scheme that minimizes the rate-distortion function while simultaneously taking the impact of quantization onto the accuracy of the network into account. Experimental results show that DeepCABAC consistently attains higher compression rates than previously proposed coding techniques for neural network compression. For instance, it is able to compress the VGG16 ImageNet model by x63.6 with no loss of accuracy, thus being able to represent the entire network with merely 8.7MB. The source code for encoding and decoding can be found at https://github.com/fraunhoferhhi/DeepCABAC.
Convolutional neural networks (CNNs) achieve state-of-the-art accuracy in a variety of tasks in computer vision and beyond. One of the major obstacles hindering the ubiquitous use of CNNs for inference on low-power edge devices is their high computational complexity and memory bandwidth requirements. The latter often dominates the energy footprint on modern hardware. In this paper, we introduce a lossy transform coding approach, inspired by image and video compression, designed to reduce the memory bandwidth due to the storage of intermediate activation calculation results. Our method does not require fine-tuning the network weights and halves the data transfer volumes to the main memory by compressing feature maps, which are highly correlated, with variable length coding. Our method outperform previous approach in term of the number of bits per value with minor accuracy degradation on ResNet-34 and MobileNetV2. We analyze the performance of our approach on a variety of CNN architectures and demonstrate that FPGA implementation of ResNet-18 with our approach results in a reduction of around 40% in the memory energy footprint, compared to quantized network, with negligible impact on accuracy. When allowing accuracy degradation of up to 2%, the reduction of 60% is achieved. A reference implementation is available at https://github.com/CompressTeam/TransformCodingInference
In this paper, we propose a quality enhancement network of versatile video coding (VVC) compressed videos by jointly exploiting spatial details and temporal structure (SDTS). The proposed network consists of a temporal structure fusion subnet and a spatial detail enhancement subnet. The former subnet is used to estimate and compensate the temporal motion across frames, and the latter subnet is used to reduce the compression artifacts and enhance the reconstruction quality of compressed video. Experimental results demonstrate the effectiveness of our SDTS-based method.
Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional video compression method and the powerful non-linear representation ability of neural networks, we propose the first end-to-end video compression deep model that jointly optimizes all the components for video compression. Specifically, learning based optical flow estimation is utilized to obtain the motion information and reconstruct the current frames. Then we employ two auto-encoder style neural networks to compress the corresponding motion and residual information. All the modules are jointly learned through a single loss function, in which they collaborate with each other by considering the trade-off between reducing the number of compression bits and improving quality of the decoded video. Experimental results show that the proposed approach can outperform the widely used video coding standard H.264 in terms of PSNR and be even on par with the latest standard H.265 in terms of MS-SSIM. Code is released at https://github.com/GuoLusjtu/DVC.
In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames. In this paper, we propose a multi-frame guided attention network (MGANet) to enhance the quality of compressed videos. Our network is composed of a temporal encoder that discovers inter-frame relations, a guided encoder-decoder subnet that encodes and enhances the visual patterns of target frame, and a multi-supervised reconstruction component that aggregates information to predict details. We design a bidirectional residual convolutional LSTM unit to implicitly discover frames variations over time with respect to the target frame. Meanwhile, the guided map is proposed to guide our network to concentrate more on the block boundary. Our approach takes advantage of intra-frame prior information and inter-frame information to improve the quality of compressed video. Experimental results show the robustness and superior performance of the proposed method.Code is available at https://github.com/mengab/MGANet
We introduce a method for learning adversarial perturbations targeted to individual images or videos. The learned perturbations are found to be sparse while at the same time containing a high level of feature detail. Thus, the extracted perturbations allow a form of object or action recognition and provide insights into what features the studied deep neural network models consider important when reaching their classification decisions. From an adversarial point of view, the sparse perturbations successfully confused the models into misclassifying, although the perturbed samples still belonged to the same original class by visual examination. This is discussed in terms of a prospective data augmentation scheme. The sparse yet high-quality perturbations may also be leveraged for image or video compression.
It has long been considered a significant problem to improve the visual quality of lossy image and video compression. Recent advances in computing power together with the availability of large training data sets has increased interest in the application of deep learning cnns to address image recognition and image processing tasks. Here, we present a powerful cnn tailored to the specific task of semantic image understanding to achieve higher visual quality in lossy compression. A modest increase in complexity is incorporated to the encoder which allows a standard, off-the-shelf jpeg decoder to be used. While jpeg encoding may be optimized for generic images, the process is ultimately unaware of the specific content of the image to be compressed. Our technique makes jpeg content-aware by designing and training a model to identify multiple semantic regions in a given image. Unlike object detection techniques, our model does not require labeling of object positions and is able to identify objects in a single pass. We present a new cnn architecture directed specifically to image compression, which generates a map that highlights semantically-salient regions so that they can be encoded at higher quality as compared to background regions. By adding a complete set of features for every class, and then taking a threshold over the sum of all feature activations, we generate a map that highlights semantically-salient regions so that they can be encoded at a better quality compared to background regions. Experiments are presented on the Kodak PhotoCD dataset and the MIT Saliency Benchmark dataset, in which our algorithm achieves higher visual quality for the same compressed size.