The many variations of Implicit Neural Representations (INRs), where a neural network is trained as a continuous representation of a signal, have tremendous practical utility for downstream tasks including novel view synthesis, video compression, and image super-resolution. Unfortunately, the inner workings of these networks are seriously under-studied. Our work, eXplaining the Implicit Neural Canvas (XINC), is a unified framework for explaining properties of INRs by examining the strength of each neuron's contribution to each output pixel. We call the aggregate of these contribution maps the Implicit Neural Canvas and we use this concept to demonstrate that the INRs we study learn to "see" the frames they represent in surprising ways. For example, INRs tend to have highly distributed representations. While lacking high-level object semantics, they have a significant bias for color and edges, and are almost entirely space-agnostic. We arrive at our conclusions by examining how objects are represented across time in video INRs, using clustering to visualize similar neurons across layers and architectures, and show that this is dominated by motion. These insights demonstrate the general usefulness of our analysis framework. Our project page is available at https://namithap10.github.io/xinc.
Video content has experienced a surge in popularity, asserting its dominance over internet traffic and Internet of Things (IoT) networks. Video compression has long been regarded as the primary means of efficiently managing the substantial multimedia traffic generated by video-capturing devices. Nevertheless, video compression algorithms entail significant computational demands in order to achieve substantial compression ratios. This complexity presents a formidable challenge when implementing efficient video coding standards in resource-constrained embedded systems, such as IoT edge node cameras. To tackle this challenge, this paper introduces NU-Class Net, an innovative deep-learning model designed to mitigate compression artifacts stemming from lossy compression codecs. This enhancement significantly elevates the perceptible quality of low-bit-rate videos. By employing the NU-Class Net, the video encoder within the video-capturing node can reduce output quality, thereby generating low-bit-rate videos and effectively curtailing both computation and bandwidth requirements at the edge. On the decoder side, which is typically less encumbered by resource limitations, NU-Class Net is applied after the video decoder to compensate for artifacts and approximate the quality of the original video. Experimental results affirm the efficacy of the proposed model in enhancing the perceptible quality of videos, especially those streamed at low bit rates.
The resource efficiency of video analytics workloads is critical for large-scale deployments on edge nodes and cloud clusters. Recent advanced systems have benefited from techniques including video compression, frame filtering, and deep model acceleration. However, based on our year-long experience of operating a real-time video analytics system on more than 1000 cameras, we identified a previously overlooked bottleneck of end-to-end concurrency: video decoding. To support concurrent video inference at scale, in this work, we investigate a new task, named video packet gating, which selectively filters packets before running a decoder. We propose a novel multi-view embedding approach for video packets and present PacketGame that has both theoretical performance guarantee and practical system designs. Experiments on both public datasets and a real system show PacketGame saves 52.0--79.3% decoding costs and achieves 2.1--4.8× concurrency compared to original workloads. Comparisons with four state-of-the-art complementary methods show the superiority of PacketGame in end-to-end concurrency.
Conditional coding has lately emerged as the mainstream approach to learned video compression. However, a recent study shows that it may perform worse than residual coding when the information bottleneck arises. Conditional residual coding was thus proposed, creating a new school of thought to improve on conditional coding. Notably, conditional residual coding relies heavily on the assumption that the residual frame has a lower entropy rate than that of the intra frame. Recognizing that this assumption is not always true due to dis-occlusion phenomena or unreliable motion estimates, we propose a masked conditional residual coding scheme. It learns a soft mask to form a hybrid of conditional coding and conditional residual coding in a pixel adaptive manner. We introduce a Transformer-based conditional autoencoder. Several strategies are investigated with regard to how to condition a Transformer-based autoencoder for inter-frame coding, a topic that is largely under-explored. Additionally, we propose a channel transform module (CTM) to decorrelate the image latents along the channel dimension, with the aim of using the simple hyperprior to approach similar compression performance to the channel-wise autoregressive model. Experimental results confirm the superiority of our masked conditional residual transformer (termed MaskCRT) to both conditional coding and conditional residual coding. On commonly used datasets, MaskCRT shows comparable BD-rate results to VTM-17.0 under the low delay P configuration in terms of PSNR-RGB and outperforms VTM-17.0 in terms of MS-SSIM-RGB. It also opens up a new research direction for advancing learned video compression.
The environmental impact of video streaming services has been discussed as part of the strategies towards sustainable information and communication technologies. A first step towards that is the energy profiling and assessment of energy consumption of existing video technologies. This paper presents a comprehensive study of power measurement techniques in video compression, comparing the use of hardware and software power meters. An experimental methodology to ensure reliability of measurements is introduced. Key findings demonstrate the high correlation of hardware and software based energy measurements for two video codecs across different spatial and temporal resolutions at a lower computational overhead.
The large amounts of data associated with 360-degree video require highly effective compression techniques for efficient storage and distribution. The development of improved motion models for 360-degree motion compensation has shown significant improvements in compression efficiency. A geodesic motion model representing translational camera motion proved to be one of the most effective models. In this paper, we propose an improved geometry-corrected geodesic motion model that outperforms the state of the art at reduced complexity. We additionally propose the transmission of per-frame camera motion information, where prior work assumed the same camera motion for all frames of a sequence. Our approach yields average Bj{\o}ntegaard Delta rate savings of 2.27% over H.266/VVC, outperforming the original geodesic motion model by 0.32 percentage points at reduced computational complexity.
Video compression is widely used in digital television, surveillance systems, and virtual reality. Real-time video decoding is crucial in practical scenarios. Recently, neural video compression (NVC) combines traditional coding with deep learning, achieving impressive compression efficiency. Nevertheless, the NVC models involve high computational costs and complex memory access patterns, challenging real-time hardware implementations. To relieve this burden, we propose an algorithm and hardware co-design framework named NVCA for video decoding on resource-limited devices. Firstly, a CNN-Transformer hybrid network is developed to improve compression performance by capturing multi-scale non-local features. In addition, we propose a fast algorithm-based sparse strategy that leverages the dual advantages of pruning and fast algorithms, sufficiently reducing computational complexity while maintaining video compression efficiency. Secondly, a reconfigurable sparse computing core is designed to flexibly support sparse convolutions and deconvolutions based on the fast algorithm-based sparse strategy. Furthermore, a novel heterogeneous layer chaining dataflow is incorporated to reduce off-chip memory traffic stemming from extensive inter-frame motion and residual information. Thirdly, the overall architecture of NVCA is designed and synthesized in TSMC 28nm CMOS technology. Extensive experiments demonstrate that our design provides superior coding quality and up to 22.7x decoding speed improvements over other video compression designs. Meanwhile, our design achieves up to 2.2x improvements in energy efficiency compared to prior accelerators.
Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded promising results. Existing methods using a single-scale Variational AutoEncoder (VAE) must devise complex networks for conditional probability estimation in latent space, neglecting multiscale characteristics of video frames. Instead, this work proposes hierarchical probabilistic predictive coding, for which hierarchal VAEs are carefully designed to characterize multiscale latent features as a family of flexible priors and posteriors to predict the probabilities of future frames. Under such a hierarchical structure, lightweight networks are sufficient for prediction. The proposed method outperforms representative learned video compression models on common testing videos and demonstrates computational friendliness with much less memory footprint and faster encoding/decoding. Extensive experiments on adaptation to temporal patterns also indicate the better generalization of our hierarchical predictive mechanism. Furthermore, our solution is the first to enable progressive decoding that is favored in networked video applications with packet loss.
Video compression systems must support increasing bandwidth and data throughput at low cost and power, and can be limited by entropy coding bottlenecks. Efficiency can be greatly improved by parallelizing coding, which can be done at much larger scales with new neural-based codecs, but with some compression loss related to data organization. We analyze the bit rate overhead needed to support multiple bitstreams for concurrent decoding, and for its minimization propose a method for compressing parallel-decoding entry points, using bidirectional bitstream packing, and a new form of jointly optimizing arithmetic coding termination. It is shown that those techniques significantly lower the overhead, making it easier to reduce it to a small fraction of the average bitstream size, like, for example, less than 1% and 0.1% when the average number of bitstream bytes is respectively larger than 95 and 1,200 bytes.
In recent years, end-to-end learnt video codecs have demonstrated their potential to compete with conventional coding algorithms in term of compression efficiency. However, most learning-based video compression models are associated with high computational complexity and latency, in particular at the decoder side, which limits their deployment in practical applications. In this paper, we present a novel model-agnostic pruning scheme based on gradient decay and adaptive layer-wise distillation. Gradient decay enhances parameter exploration during sparsification whilst preventing runaway sparsity and is superior to the standard Straight-Through Estimation. The adaptive layer-wise distillation regulates the sparse training in various stages based on the distortion of intermediate features. This stage-wise design efficiently updates parameters with minimal computational overhead. The proposed approach has been applied to three popular end-to-end learnt video codecs, FVC, DCVC, and DCVC-HEM. Results confirm that our method yields up to 65% reduction in MACs and 2x speed-up with less than 0.3dB drop in BD-PSNR. Supporting code and supplementary material can be downloaded from: https://jasminepp.github.io/lightweightdvc/
Most neural compression models are trained on large datasets of images or videos in order to generalize to unseen data. Such generalization typically requires large and expressive architectures with a high decoding complexity. Here we introduce C3, a neural compression method with strong rate-distortion (RD) performance that instead overfits a small model to each image or video separately. The resulting decoding complexity of C3 can be an order of magnitude lower than neural baselines with similar RD performance. C3 builds on COOL-CHIC (Ladune et al.) and makes several simple and effective improvements for images. We further develop new methodology to apply C3 to videos. On the CLIC2020 image benchmark, we match the RD performance of VTM, the reference implementation of the H.266 codec, with less than 3k MACs/pixel for decoding. On the UVG video benchmark, we match the RD performance of the Video Compression Transformer (Mentzer et al.), a well-established neural video codec, with less than 5k MACs/pixel for decoding.
With the increasing consumption of 3D displays and virtual reality, multi-view video has become a promising format. However, its high resolution and multi-camera shooting result in a substantial increase in data volume, making storage and transmission a challenging task. To tackle these difficulties, we propose an implicit-explicit integrated representation for multi-view video compression. Specifically, we first use the explicit representation-based 2D video codec to encode one of the source views. Subsequently, we propose employing the implicit neural representation (INR)-based codec to encode the remaining views. The implicit codec takes the time and view index of multi-view video as coordinate inputs and generates the corresponding implicit reconstruction frames.To enhance the compressibility, we introduce a multi-level feature grid embedding and a fully convolutional architecture into the implicit codec. These components facilitate coordinate-feature and feature-RGB mapping, respectively. To further enhance the reconstruction quality from the INR codec, we leverage the high-quality reconstructed frames from the explicit codec to achieve inter-view compensation. Finally, the compensated results are fused with the implicit reconstructions from the INR to obtain the final reconstructed frames. Our proposed framework combines the strengths of both implicit neural representation and explicit 2D codec. Extensive experiments conducted on public datasets demonstrate that the proposed framework can achieve comparable or even superior performance to the latest multi-view video compression standard MIV and other INR-based schemes in terms of view compression and scene modeling.
Neural fields, mapping low-dimensional input coordinates to corresponding signals, have shown promising results in representing various signals. Numerous methodologies have been proposed, and techniques employing MLPs and grid representations have achieved substantial success. MLPs allow compact and high expressibility, yet often suffer from spectral bias and slow convergence speed. On the other hand, methods using grids are free from spectral bias and achieve fast training speed, however, at the expense of high spatial complexity. In this work, we propose a novel way for exploiting both MLPs and grid representations in neural fields. Unlike the prevalent methods that combine them sequentially (extract features from the grids first and feed them to the MLP), we inject spectral bias-free grid representations into the intermediate features in the MLP. More specifically, we suggest a Coordinate-Aware Modulation (CAM), which modulates the intermediate features using scale and shift parameters extracted from the grid representations. This can maintain the strengths of MLPs while mitigating any remaining potential biases, facilitating the rapid learning of high-frequency components. In addition, we empirically found that the feature normalizations, which have not been successful in neural filed literature, proved to be effective when applied in conjunction with the proposed CAM. Experimental results demonstrate that CAM enhances the performance of neural representation and improves learning stability across a range of signals. Especially in the novel view synthesis task, we achieved state-of-the-art performance with the least number of parameters and fast training speed for dynamic scenes and the best performance under 1MB memory for static scenes. CAM also outperforms the best-performing video compression methods using neural fields by a large margin.
Ensuring high-quality video content for wireless users has become increasingly vital. Nevertheless, maintaining a consistent level of video quality faces challenges due to the fluctuating encoded bitrate, primarily caused by dynamic video content, especially in live streaming scenarios. Video compression is typically employed to eliminate unnecessary redundancies within and between video frames, thereby reducing the required bandwidth for video transmission. The encoded bitrate and the quality of the compressed video depend on encoder parameters, specifically, the quantization parameter (QP). Poor choices of encoder parameters can result in reduced bandwidth efficiency and high likelihood of non-conformance. Non-conformance refers to the violation of the peak signal-to-noise ratio (PSNR) constraint for an encoded video segment. To address these issues, a real-time deep learning-based H.264 controller is proposed. This controller dynamically estimates the optimal encoder parameters based on the content of a video chunk with minimal delay. The objective is to maintain video quality in terms of PSNR above a specified threshold while minimizing the average bitrate of the compressed video. Experimental results, conducted on both QCIF dataset and a diverse range of random videos from public datasets, validate the effectiveness of this approach. Notably, it achieves improvements of up to 2.5 times in average bandwidth usage compared to the state-of-the-art adaptive bitrate video streaming, with a negligible non-conformance probability below $10^{-2}$.
Existing video compression (VC) methods primarily aim to reduce the spatial and temporal redundancies between consecutive frames in a video while preserving its quality. In this regard, previous works have achieved remarkable results on videos acquired under specific settings such as instant (known) exposure time and shutter speed which often result in sharp videos. However, when these methods are evaluated on videos captured under different temporal priors, which lead to degradations like motion blur and low frame rate, they fail to maintain the quality of the contents. In this work, we tackle the VC problem in a general scenario where a given video can be blurry due to predefined camera settings or dynamics in the scene. By exploiting the natural trade-off between visual enhancement and data compression, we formulate VC as a min-max optimization problem and propose an effective framework and training strategy to tackle the problem. Extensive experimental results on several benchmark datasets confirm the effectiveness of our method compared to several state-of-the-art VC approaches.
In the latest years, videoconferencing has taken a fundamental role in interpersonal relations, both for personal and business purposes. Lossy video compression algorithms are the enabling technology for videoconferencing, as they reduce the bandwidth required for real-time video streaming. However, lossy video compression decreases the perceived visual quality. Thus, many techniques for reducing compression artifacts and improving video visual quality have been proposed in recent years. In this work, we propose a novel GAN-based method for compression artifacts reduction in videoconferencing. Given that, in this context, the speaker is typically in front of the camera and remains the same for the entire duration of the transmission, we can maintain a set of reference keyframes of the person from the higher-quality I-frames that are transmitted within the video stream and exploit them to guide the visual quality improvement; a novel aspect of this approach is the update policy that maintains and updates a compact and effective set of reference keyframes. First, we extract multi-scale features from the compressed and reference frames. Then, our architecture combines these features in a progressive manner according to facial landmarks. This allows the restoration of the high-frequency details lost after the video compression. Experiments show that the proposed approach improves visual quality and generates photo-realistic results even with high compression rates. Code and pre-trained networks are publicly available at https://github.com/LorenzoAgnolucci/Keyframes-GAN.
In the blind single image super-resolution (SISR) task, existing works have been successful in restoring image-level unknown degradations. However, when a single video frame becomes the input, these works usually fail to address degradations caused by video compression, such as mosquito noise, ringing, blockiness, and staircase noise. In this work, we for the first time, present a video compression-based degradation model to synthesize low-resolution image data in the blind SISR task. Our proposed image synthesizing method is widely applicable to existing image datasets, so that a single degraded image can contain distortions caused by the lossy video compression algorithms. This overcomes the leak of feature diversity in video data and thus retains the training efficiency. By introducing video coding artifacts to SISR degradation models, neural networks can super-resolve images with the ability to restore video compression degradations, and achieve better results on restoring generic distortions caused by image compression as well. Our proposed approach achieves superior performance in SOTA no-reference Image Quality Assessment, and shows better visual quality on various datasets. In addition, we evaluate the SISR neural network trained with our degradation model on video super-resolution (VSR) datasets. Compared to architectures specifically designed for the VSR purpose, our method exhibits similar or better performance, evidencing that the presented strategy on infusing video-based degradation is generalizable to address more complicated compression artifacts even without temporal cues.
In recent years, the proliferation of multimedia applications and formats, such as IPTV, Virtual Reality (VR, 360-degree), and point cloud videos, has presented new challenges to the video compression research community. Simultaneously, there has been a growing demand from users for higher resolutions and improved visual quality. To further enhance coding efficiency, a new video coding standard, Versatile Video Coding (VVC), was introduced in July 2020. This paper conducts a comprehensive analysis of coding performance and complexity for the latest VVC standard in comparison to its predecessor, High Efficiency Video Coding (HEVC). The study employs a diverse set of test sequences, covering both High Definition (HD) and Ultra High Definition (UHD) resolutions, and spans a wide range of bit-rates. These sequences are encoded using the reference software encoders of HEVC (HM) and VVC (VTM). The results consistently demonstrate that VVC outperforms HEVC, achieving bit-rate savings of up to 40% on the subjective quality scale, particularly at realistic bit-rates and quality levels. Objective quality metrics, including PSNR, SSIM, and VMAF, support these findings, revealing bit-rate savings ranging from 31% to 40%, depending on the video content, spatial resolution, and the selected quality metric. However, these improvements in coding efficiency come at the cost of significantly increased computational complexity. On average, our results indicate that the VVC decoding process is 1.5 times more complex, while the encoding process becomes at least eight times more complex than that of the HEVC reference encoder. Our simultaneous profiling of the two standards sheds light on the primary evolutionary differences between them and highlights the specific stages responsible for the observed increase in complexity.
Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove inter-frame redundancy. However, inaccurate motion vector (MV) usually lead to the distortion of reconstructed frame. In addition, most approaches ignore the spatial and channel redundancy. To solve above problems, we propose a motion-aware and spatial-temporal-channel contextual coding based video compression network (MASTC-VC), which learns the latent representation and uses variational autoencoders (VAEs) to capture the characteristics of intra-frame pixels and inter-frame motion. Specifically, we design a multiscale motion-aware module (MS-MAM) to estimate spatial-temporal-channel consistent motion vector by utilizing the multiscale motion prediction information in a coarse-to-fine way. On the top of it, we further propose a spatial-temporal-channel contextual module (STCCM), which explores the correlation of latent representation to reduce the bit consumption from spatial, temporal and channel aspects respectively. Comprehensive experiments show that our proposed MASTC-VC is surprior to previous state-of-the-art (SOTA) methods on three public benchmark datasets. More specifically, our method brings average 10.15\% BD-rate savings against H.265/HEVC (HM-16.20) in PSNR metric and average 23.93\% BD-rate savings against H.266/VVC (VTM-13.2) in MS-SSIM metric.
Under certain circumstances, advanced neural video codecs can surpass the most complex traditional codecs in their rate-distortion (RD) performance. One of the main reasons for the high performance of existing neural video codecs is the use of the entropy model, which can provide more accurate probability distribution estimations for compressing the latents. This also implies the rigorous requirement that entropy models running on different platforms should use consistent distribution estimations. However, in cross-platform scenarios, entropy models running on different platforms usually yield inconsistent probability distribution estimations due to floating point computation errors that are platform-dependent, which can cause the decoding side to fail in correctly decoding the compressed bitstream sent by the encoding side. In this paper, we propose a cross-platform video compression framework based on codebooks, which avoids autoregressive entropy modeling and achieves video compression by transmitting the index sequence of the codebooks. Moreover, instead of using optical flow for context alignment, we propose to use the conditional cross-attention module to obtain the context between frames. Due to the absence of autoregressive modeling and optical flow alignment, we can design an extremely minimalist framework that can greatly benefit computational efficiency. Importantly, our framework no longer contains any distribution estimation modules for entropy modeling, and thus computations across platforms are not necessarily consistent. Experimental results show that our method can outperform the traditional H.265 (medium) even without any entropy constraints, while achieving the cross-platform property intrinsically.