We propose a new Generative Adversarial Network for Compressed Video quality Enhancement (CVEGAN). The CVEGAN generator benefits from the use of a novel Mul2Res block (with multiple levels of residual learning branches), an enhanced residual non-local block (ERNB) and an enhanced convolutional block attention module (ECBAM). The ERNB has also been employed in the discriminator to improve the representational capability. The training strategy has also been re-designed specifically for video compression applications, to employ a relativistic sphere GAN (ReSphereGAN) training methodology together with new perceptual loss functions. The proposed network has been fully evaluated in the context of two typical video compression enhancement tools: post-processing (PP) and spatial resolution adaptation (SRA). CVEGAN has been fully integrated into the MPEG HEVC video coding test model (HM16.20) and experimental results demonstrate significant coding gains (up to 28% for PP and 38% for SRA compared to the anchor) over existing state-of-the-art architectures for both coding tools across multiple datasets.
This paper presents CompressAI, a platform that provides custom operations, layers, models and tools to research, develop and evaluate end-to-end image and video compression codecs. In particular, CompressAI includes pre-trained models and evaluation tools to compare learned methods with traditional codecs. Multiple models from the state-of-the-art on learned end-to-end compression have thus been reimplemented in PyTorch and trained from scratch. We also report objective comparison results using PSNR and MS-SSIM metrics vs. bit-rate, using the Kodak image dataset as test set. Although this framework currently implements models for still-picture compression, it is intended to be soon extended to the video compression domain.
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models. We draw a connection between such autoregressive generative models and the task of lossy video compression. Specifically, we view recent neural video compression methods (Lu et al., 2019; Yang et al., 2020b; Agustssonet al., 2020) as instances of a generalized stochastic temporal autoregressive transform, and propose avenues for enhancement based on this insight. Comprehensive evaluations on large-scale video data show improved rate-distortion performance over both state-of-the-art neural and conventional video compression methods.
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.
Color filter array is spatial multiplexing of pixel-sized filters placed over pixel detectors in camera sensors. The state-of-the-art lossless coding techniques of raw sensor data captured by such sensors leverage spatial or cross-color correlation using lifting schemes. In this paper, we propose a lifting-based lossless white balance algorithm. When applied to the raw sensor data, the spatial bandwidth of the implied chrominance signals decreases. We propose to use this white balance as a pre-processing step to lossless CFA subsampled image/video compression, improving the overall coding efficiency of the raw sensor data.
In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content. Among various compression tools, post-processing can be applied on reconstructed video content to mitigate visible compression artefacts and to enhance overall perceptual quality. Inspired by advances in deep learning, we propose a new CNN-based post-processing approach, which has been integrated with two state-of-the-art coding standards, VVC and AV1. The results show consistent coding gains on all tested sequences at various spatial resolutions, with average bit rate savings of 4.0% and 5.8% against original VVC and AV1 respectively (based on the assessment of PSNR). This network has also been trained with perceptually inspired loss functions, which have further improved reconstruction quality based on perceptual quality assessment (VMAF), with average coding gains of 13.9% over VVC and 10.5% against AV1.
In the learning based video compression approaches, it is an essential issue to compress pixel-level optical flow maps by developing new motion vector (MV) encoders. In this work, we propose a new framework called Resolution-adaptive Flow Coding (RaFC) to effectively compress the flow maps globally and locally, in which we use multi-resolution representations instead of single-resolution representations for both the input flow maps and the output motion features of the MV encoder. To handle complex or simple motion patterns globally, our frame-level scheme RaFC-frame automatically decides the optimal flow map resolution for each video frame. To cope different types of motion patterns locally, our block-level scheme called RaFC-block can also select the optimal resolution for each local block of motion features. In addition, the rate-distortion criterion is applied to both RaFC-frame and RaFC-block and select the optimal motion coding mode for effective flow coding. Comprehensive experiments on four benchmark datasets HEVC, VTL, UVG and MCL-JCV clearly demonstrate the effectiveness of our overall RaFC framework after combing RaFC-frame and RaFC-block for video compression.
Under the limited storage, computing and network bandwidth resources, the video compression coding technology plays an important role for visual communication. To efficiently compress raw video data, a colorization-based video compression coding method is proposed in this paper. In the proposed encoder, only the video luminance components are encoded and transmitted. To restore the video chrominance information, a generative adversarial network (GAN) model is adopted in the proposed decoder. In order to make the GAN work efficiently for video colorization, the generator of the proposed GAN model adopts an optimized MultiResUNet, an attention module, and a mixed loss function. Experimental results show that when compared with the H.265/HEVC video compression coding standard using all-intra coding structure, the proposed video compression coding method achieves an average of 72.05% BDBR reduction, and an average of 4.758 dB BDPSNR increase. Moreover, to our knowledge, this is the first work which compresses videos by using GAN-based colorization, and it provides a new way for addressing the video compression coding problems.
Compression has been an important research topic for many decades, to produce a significant impact on data transmission and storage. Recent advances have shown a great potential of learning image and video compression. Inspired from related works, in this paper, we present an image compression architecture using a convolutional autoencoder, and then generalize image compression to video compression, by adding an interpolation loop into both encoder and decoder sides. Our basic idea is to realize spatial-temporal energy compaction in learning image and video compression. Thereby, we propose to add a spatial energy compaction-based penalty into loss function, to achieve higher image compression performance. Furthermore, based on temporal energy distribution, we propose to select the number of frames in one interpolation loop, adapting to the motion characteristics of video contents. Experimental results demonstrate that our proposed image compression outperforms the latest image compression standard with MS-SSIM quality metric, and provides higher performance compared with state-of-the-art learning compression methods at high bit rates, which benefits from our spatial energy compaction approach. Meanwhile, our proposed video compression approach with temporal energy compaction can significantly outperform MPEG-4 and is competitive with commonly used H.264. Both our image and video compression can produce more visually pleasant results than traditional standards.
We propose a very simple and efficient video compression framework that only focuses on modeling the conditional entropy between frames. Unlike prior learning-based approaches, we reduce complexity by not performing any form of explicit transformations between frames and assume each frame is encoded with an independent state-of-the-art deep image compressor. We first show that a simple architecture modeling the entropy between the image latent codes is as competitive as other neural video compression works and video codecs while being much faster and easier to implement. We then propose a novel internal learning extension on top of this architecture that brings an additional 10% bitrate savings without trading off decoding speed. Importantly, we show that our approach outperforms H.265 and other deep learning baselines in MS-SSIM on higher bitrate UVG video, and against all video codecs on lower framerates, while being thousands of times faster in decoding than deep models utilizing an autoregressive entropy model.
Conventional video compression methods employ a linear transform and block motion model, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to combinatorial nature of the end-to-end optimization problem. Learned video compression allows end-to-end rate-distortion optimized training of all nonlinear modules, quantization parameter and entropy model simultaneously. While previous work on learned video compression considered training a sequential video codec based on end-to-end optimization of cost averaged over pairs of successive frames, it is well-known in conventional video compression that hierarchical, bi-directional coding outperforms sequential compression. In this paper, we propose for the first time end-to-end optimization of a hierarchical, bi-directional motion compensated learned codec by accumulating cost function over fixed-size groups of pictures (GOP). Experimental results show that the rate-distortion performance of our proposed learned bi-directional {\it GOP coder} outperforms the state-of-the-art end-to-end optimized learned sequential compression as expected.
We propose a novel deep multi-modality neural network for restoring very low bit rate videos of talking heads. Such video contents are very common in social media, teleconferencing, distance education, tele-medicine, etc., and often need to be transmitted with limited bandwidth. The proposed CNN method exploits the correlations among three modalities, video, audio and emotion state of the speaker, to remove the video compression artifacts caused by spatial down sampling and quantization. The deep learning approach turns out to be ideally suited for the video restoration task, as the complex non-linear cross-modality correlations are very difficult to model analytically and explicitly. The new method is a video post processor that can significantly boost the perceptual quality of aggressively compressed talking head videos, while being fully compatible with all existing video compression standards.
It has recently been demonstrated that spatial resolution adaptation can be integrated within video compression to improve overall coding performance by spatially down-sampling before encoding and super-resolving at the decoder. Significant improvements have been reported when convolutional neural networks (CNNs) were used to perform the resolution up-sampling. However, this approach suffers from high complexity at the decoder due to the employment of CNN-based super-resolution. In this paper, a novel framework is proposed which supports the flexible allocation of complexity between the encoder and decoder. This approach employs a CNN model for video down-sampling at the encoder and uses a Lanczos3 filter to reconstruct full resolution at the decoder. The proposed method was integrated into the HEVC HM 16.20 software and evaluated on JVET UHD test sequences using the All Intra configuration. The experimental results demonstrate the potential of the proposed approach, with significant bitrate savings (more than 10%) over the original HEVC HM, coupled with reduced computational complexity at both encoder (29%) and decoder (10%).
Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks. Whilst the reported performance of these approaches is impressive, this study investigates the hitherto unapproached question of the impact of commonplace image and video compression techniques on the performance of such deep learning architectures. Focusing on the JPEG and H.264 (MPEG-4 AVC) as a representative proxy for contemporary lossy image/video compression techniques that are in common use within network-connected image/video devices and infrastructure, we examine the impact on performance across five discrete tasks: human pose estimation, semantic segmentation, object detection, action recognition, and monocular depth estimation. As such, within this study we include a variety of network architectures and domains spanning end-to-end convolution, encoder-decoder, region-based CNN (R-CNN), dual-stream, and generative adversarial networks (GAN). Our results show a non-linear and non-uniform relationship between network performance and the level of lossy compression applied. Notably, performance decreases significantly below a JPEG quality (quantization) level of 15% and a H.264 Constant Rate Factor (CRF) of 40. However, retraining said architectures on pre-compressed imagery conversely recovers network performance by up to 78.4% in some cases. Furthermore, there is a correlation between architectures employing an encoder-decoder pipeline and those that demonstrate resilience to lossy image compression. The characteristics of the relationship between input compression to output task performance can be used to inform design decisions within future image/video devices and infrastructure.
We present an efficient finetuning methodology for neural-network filters which are applied as a postprocessing artifact-removal step in video coding pipelines. The fine-tuning is performed at encoder side to adapt the neural network to the specific content that is being encoded. In order to maximize the PSNR gain and minimize the bitrate overhead, we propose to finetune only the convolutional layers' biases. The proposed method achieves convergence much faster than conventional finetuning approaches, making it suitable for practical applications. The weight-update can be included into the video bitstream generated by the existing video codecs. We show that our method achieves up to 9.7% average BD-rate gain when compared to the state-of-art Versatile Video Coding (VVC) standard codec on 7 test sequences.
In this paper, we propose a novel convolutional neural network (CNN) architecture, MFRNet, for post-processing (PP) and in-loop filtering (ILF) in the context of video compression. This network consists of four Multi-level Feature review Residual dense Blocks (MFRBs), which are connected using a cascading structure. Each MFRB extracts features from multiple convolutional layers using dense connections and a multi-level residual learning structure. In order to further improve information flow between these blocks, each of them also reuses high dimensional features from the previous MFRB. This network has been integrated into PP and ILF coding modules for both HEVC (HM 16.20) and VVC (VTM 7.0), and fully evaluated under the JVET Common Test Conditions using the Random Access configuration. The experimental results show significant and consistent coding gains over both anchor codecs (HEVC HM and VVC VTM) and also over other existing CNN-based PP/ILF approaches based on Bjontegaard Delta measurements using both PSNR and VMAF for quality assessment. When MFRNet is integrated into HM 16.20, gains up to 16.0% (BD-rate VMAF) are demonstrated for ILF, and up to 21.0% (BD-rate VMAF) for PP. The respective gains for VTM 7.0 are up to 5.1% for ILF and up to 7.1% for PP.
Over the past two decades, traditional block-based video coding has made remarkable progress and spawned a series of well-known standards such as MPEG-4, H.264/AVC and H.265/HEVC. On the other hand, deep neural networks (DNNs) have shown their powerful capacity for visual content understanding, feature extraction and compact representation. Some previous works have explored the learnt video coding algorithms in an end-to-end manner, which show the great potential compared with traditional methods. In this paper, we propose an end-to-end deep neural video coding framework (NVC), which uses variational autoencoders (VAEs) with joint spatial and temporal prior aggregation (PA) to exploit the correlations in intra-frame pixels, inter-frame motions and inter-frame compensation residuals, respectively. Novel features of NVC include: 1) To estimate and compensate motion over a large range of magnitudes, we propose an unsupervised multiscale motion compensation network (MS-MCN) together with a pyramid decoder in the VAE for coding motion features that generates multiscale flow fields, 2) we design a novel adaptive spatiotemporal context model for efficient entropy coding for motion information, 3) we adopt nonlocal attention modules (NLAM) at the bottlenecks of the VAEs for implicit adaptive feature extraction and activation, leveraging its high transformation capacity and unequal weighting with joint global and local information, and 4) we introduce multi-module optimization and a multi-frame training strategy to minimize the temporal error propagation among P-frames. NVC is evaluated for the low-delay causal settings and compared with H.265/HEVC, H.264/AVC and the other learnt video compression methods following the common test conditions, demonstrating consistent gains across all popular test sequences for both PSNR and MS-SSIM distortion metrics.
In this paper, a mode selection network (ModeNet) is proposed to enhance deep learning-based video compression. Inspired by traditional video coding, ModeNet purpose is to enable competition among several coding modes. The proposed ModeNet learns and conveys a pixel-wise partitioning of the frame, used to assign each pixel to the most suited coding mode. ModeNet is trained alongside the different coding modes to minimize a rate-distortion cost. It is a flexible component which can be generalized to other systems to allow competition between different coding tools. Mod-eNet interest is studied on a P-frame coding task, where it is used to design a method for coding a frame given its prediction. ModeNet-based systems achieve compelling performance when evaluated under the Challenge on Learned Image Compression 2020 (CLIC20) P-frame coding track conditions.
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.