We propose a new transformer-based image and video tokenizer with Binary Spherical Quantization (BSQ). BSQ projects the high-dimensional visual embedding to a lower-dimensional hypersphere and then applies binary quantization. BSQ is (1) parameter-efficient without an explicit codebook, (2) scalable to arbitrary token dimensions, and (3) compact: compressing visual data by up to 100$\times$ with minimal distortion. Our tokenizer uses a transformer encoder and decoder with simple block-wise causal masking to support variable-length videos as input. The resulting BSQ-ViT achieves state-of-the-art visual reconstruction quality on image and video reconstruction benchmarks with 2.4$\times$ throughput compared to the best prior methods. Furthermore, by learning an autoregressive prior for adaptive arithmetic coding, BSQ-ViT achieves comparable results on video compression with state-of-the-art video compression standards. BSQ-ViT also enables masked language models to achieve competitive image synthesis quality to GAN- and diffusion-based methods.
Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream video analysis tasks. In this paper, we propose a Masked Video Modeling (MVM)-powered compression framework that particularly preserves video semantics, by jointly mining and compressing the semantics in a self-supervised manner. While MVM is proficient at learning generalizable semantics through the masked patch prediction task, it may also encode non-semantic information like trivial textural details, wasting bitcost and bringing semantic noises. To suppress this, we explicitly regularize the non-semantic entropy of the compressed video in the MVM token space. The proposed framework is instantiated as a simple Semantic-Mining-then-Compression (SMC) model. Furthermore, we extend SMC as an advanced SMC++ model from several aspects. First, we equip it with a masked motion prediction objective, leading to better temporal semantic learning ability. Second, we introduce a Transformer-based compression module, to improve the semantic compression efficacy. Considering that directly mining the complex redundancy among heterogeneous features in different coding stages is non-trivial, we introduce a compact blueprint semantic representation to align these features into a similar form, fully unleashing the power of the Transformer-based compression module. Extensive results demonstrate the proposed SMC and SMC++ models show remarkable superiority over previous traditional, learnable, and perceptual quality-oriented video codecs, on three video analysis tasks and seven datasets. \textit{Codes and model are available at: \url{https://github.com/tianyuan168326/VideoSemanticCompression-Pytorch}.
Beyond the exploration of traditional spatial, temporal and subjective visual signal redundancy in image and video compression, recent research has focused on leveraging cross-color component redundancy to enhance coding efficiency. Cross-component coding approaches are motivated by the statistical correlations among different color components, such as those in the Y'CbCr color space, where luma (Y) color component typically exhibits finer details than chroma (Cb/Cr) color components. Inspired by previous cross-component coding algorithms, this paper introduces a novel in-loop filtering approach named Cross-Component Sample Offset (CCSO). CCSO utilizes co-located and neighboring luma samples to generate correction signals for both luma and chroma reconstructed samples. It is a multiplication-free, non-linear mapping process implemented using a look-up-table. The input to the mapping is a group of reconstructed luma samples, and the output is an offset value applied on the center luma or co-located chroma sample. Experimental results demonstrate that the proposed CCSO can be applied to both image and video coding, resulting in improved coding efficiency and visual quality. The method has been adopted into an experimental next-generation video codec beyond AV1 developed by the Alliance for Open Media (AOMedia), achieving significant objective coding gains up to 3.5\,\% and 1.8\,\% for PSNR and VMAF quality metrics, respectively, under random access configuration. Additionally, CCSO notably improves the subjective visual quality.
With the exponential growth of video traffic, traditional video streaming systems are approaching their limits in compression efficiency and communication capacity. To further reduce bitrate while maintaining quality, we propose Promptus, a disruptive semantic communication system that streaming prompts instead of video content, which represents real-world video frames with a series of "prompts" for delivery and employs Stable Diffusion to generate videos at the receiver. To ensure that the generated video is pixel-aligned with the original video, a gradient descent-based prompt fitting framework is proposed. Further, a low-rank decomposition-based bitrate control algorithm is introduced to achieve adaptive bitrate. For inter-frame compression, an interpolation-aware fitting algorithm is proposed. Evaluations across various video genres demonstrate that, compared to H.265, Promptus can achieve more than a 4x bandwidth reduction while preserving the same perceptual quality. On the other hand, at extremely low bitrates, Promptus can enhance the perceptual quality by 0.139 and 0.118 (in LPIPS) compared to VAE and H.265, respectively, and decreases the ratio of severely distorted frames by 89.3% and 91.7%. Our work opens up a new paradigm for efficient video communication. Promptus is open-sourced at: https://github.com/JiangkaiWu/Promptus.
Video compression aims to reconstruct seamless frames by encoding the motion and residual information from existing frames. Previous neural video compression methods necessitate distinct codecs for three types of frames (I-frame, P-frame and B-frame), which hinders a unified approach and generalization across different video contexts. Intra-codec techniques lack the advanced Motion Estimation and Motion Compensation (MEMC) found in inter-codec, leading to fragmented frameworks lacking uniformity. Our proposed Intra- & Inter-frame Video Compression (I$^2$VC) framework employs a single spatio-temporal codec that guides feature compression rates according to content importance. This unified codec transforms the dependence across frames into a conditional coding scheme, thus integrating intra- and inter-frame compression into one cohesive strategy. Given the absence of explicit motion data, achieving competent inter-frame compression with only a conditional codec poses a challenge. To resolve this, our approach includes an implicit inter-frame alignment mechanism. With the pre-trained diffusion denoising process, the utilization of a diffusion-inverted reference feature rather than random noise supports the initial compression state. This process allows for selective denoising of motion-rich regions based on decoded features, facilitating accurate alignment without the need for MEMC. Our experimental findings, across various compression configurations (AI, LD and RA) and frame types, prove that I$^2$VC outperforms the state-of-the-art perceptual learned codecs. Impressively, it exhibits a 58.4% enhancement in perceptual reconstruction performance when benchmarked against the H.266/VVC standard (VTM). Official implementation can be found at https://github.com/GYukai/I2VC.
Field-captured video facilitates detailed studies of spatio-temporal aspects of animal locomotion, decision-making and environmental interactions including predator-prey relationships and habitat utilisation. But even though data capture is cheap with mass-produced hardware, storage, processing and transmission overheads provide a hurdle to acquisition of high resolution video from field-situated edge computing devices. Efficient compression algorithms are therefore essential if monitoring is to be conducted on single-board computers in situations where such hurdles must be overcome. Animal motion tracking in the field has unique characteristics that necessitate the use of novel video compression techniques, which may be underexplored or unsuitable in other contexts. In this article, we therefore introduce a new motion analysis-based video compression algorithm specifically designed for camera traps. We implemented and tested this algorithm using a case study of insect-pollinator motion tracking on three popular edge computing platforms. The algorithm identifies and stores only image regions depicting motion relevant to pollination monitoring, reducing overall data size by an average of 87% across diverse test datasets. Our experiments demonstrate the algorithm's capability to preserve critical information for insect behaviour analysis through both manual observation and automatic analysis of the compressed footage. The method presented in this paper enhances the applicability of low-powered computer vision edge devices to remote, in situ animal motion monitoring, and improves the efficiency of playback during behavioural analyses. Our new software, EcoMotionZip, is available Open Access.
Learned wavelet image and video coding approaches provide an explainable framework with a latent space corresponding to a wavelet decomposition. The wavelet image coder iWave++ achieves state-of-the-art performance and has been employed for various compression tasks, including lossy as well as lossless image, video, and medical data compression. However, the approaches suffer from slow decoding speed due to the autoregressive context model used in iWave++. In this paper, we show how a parallelized context model can be integrated into the iWave++ framework. Our experimental results demonstrate a speedup factor of over 350 and 240 for image and video compression, respectively. At the same time, the rate-distortion performance in terms of Bj{\o}ntegaard delta bitrate is slightly worse by 1.5\% for image coding and 1\% for video coding. In addition, we analyze the learned wavelet decomposition by visualizing its subband impulse responses.
Learning-based Neural Video Codecs (NVCs) have emerged as a compelling alternative to standard video codecs, demonstrating promising performance, and simple and easily maintainable pipelines. However, NVCs often fall short of compression performance and occasionally exhibit poor generalization capability due to inference-only compression scheme and their dependence on training data. The instance-adaptive video compression techniques have recently been suggested as a viable solution, fine-tuning the encoder or decoder networks for a particular test instance video. However, fine-tuning all the model parameters incurs high computational costs, increases the bitrates, and often leads to unstable training. In this work, we propose a parameter-efficient instance-adaptive video compression framework. Inspired by the remarkable success of parameter-efficient fine-tuning on large-scale neural network models, we propose to use a lightweight adapter module that can be easily attached to the pretrained NVCs and fine-tuned for test video sequences. The resulting algorithm significantly improves compression performance and reduces the encoding time compared to the existing instant-adaptive video compression algorithms. Furthermore, the suggested fine-tuning method enhances the robustness of the training process, allowing for the proposed method to be widely used in many practical settings. We conducted extensive experiments on various standard benchmark datasets, including UVG, MCL-JVC, and HEVC sequences, and the experimental results have shown a significant improvement in rate-distortion (RD) curves (up to 5 dB PSNR) and BD rates compared to the baselines NVC. Our code is available on https://github.com/ohsngjun/PEVC.
Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents. Although these methods have been very practical in neural image compression (NIC), their application in neural video compression (NVC) is still limited due to two main aspects: 1), video compression relies heavily on temporal redundancy, therefore updating just one or a few frames can lead to significant errors accumulating over time; 2), NVC frameworks are generally more complex, with many large components that are not easy to update quickly during encoding. To address the previously mentioned challenges, we have developed a content-adaptive NVC technique called Group-aware Parameter-Efficient Updating (GPU). Initially, to minimize error accumulation, we adopt a group-aware approach for updating encoder parameters. This involves adopting a patch-based Group of Pictures (GoP) training strategy to segment a video into patch-based GoPs, which will be updated to facilitate a globally optimized domain-transferable solution. Subsequently, we introduce a parameter-efficient delta-tuning strategy, which is achieved by integrating several light-weight adapters into each coding component of the encoding process by both serial and parallel configuration. Such architecture-agnostic modules stimulate the components with large parameters, thereby reducing both the update cost and the encoding time. We incorporate our GPU into the latest NVC framework and conduct comprehensive experiments, whose results showcase outstanding video compression efficiency across four video benchmarks and adaptability of one medical image benchmark.
Recent advancements in data-driven approaches for remote photoplethysmography (rPPG) have significantly improved the accuracy of remote heart rate estimation. However, the performance of such approaches worsens considerably under video compression, which is nevertheless necessary to store and transmit video data efficiently. In this paper, we present a novel approach to address the impact of video compression on rPPG estimation, which leverages a pulse-signal magnification transformation to adapt compressed videos to an uncompressed data domain in which the rPPG signal is magnified. We validate the effectiveness of our model by exhaustive evaluations on two publicly available datasets, UCLA-rPPG and UBFC-rPPG, employing both intra- and cross-database performance at several compression rates. Additionally, we assess the robustness of our approach on two additional highly compressed and widely-used datasets, MAHNOB-HCI and COHFACE, which reveal outstanding heart rate estimation results.
Stereoscopic video conferencing is still challenging due to the need to compress stereo RGB-D video in real-time. Though hardware implementations of standard video codecs such as H.264 / AVC and HEVC are widely available, they are not designed for stereoscopic videos and suffer from reduced quality and performance. Specific multiview or 3D extensions of these codecs are complex and lack efficient implementations. In this paper, we propose a new approach to upgrade a 2D video codec to support stereo RGB-D video compression, by wrapping it with a neural pre- and post-processor pair. The neural networks are end-to-end trained with an image codec proxy, and shown to work with a more sophisticated video codec. We also propose a geometry-aware loss function to improve rendering quality. We train the neural pre- and post-processors on a synthetic 4D people dataset, and evaluate it on both synthetic and real-captured stereo RGB-D videos. Experimental results show that the neural networks generalize well to unseen data and work out-of-box with various video codecs. Our approach saves about 30% bit-rate compared to a conventional video coding scheme and MV-HEVC at the same level of rendering quality from a novel view, without the need of a task-specific hardware upgrade.
In an adaptive bitrate streaming application, the efficiency of video compression and the encoded video quality depend on both the video codec and the quality metric used to perform encoding optimization. The development of such a quality metric need large scale subjective datasets. In this work we merge several datasets into one to support the creation of a metric tailored for video compression and scaling. We proposed a set of HEVC lightweight features to boost performance of the metrics. Our metrics can be computed from tightly coupled encoding process with 4% compute overhead or from the decoding process in real-time. The proposed method can achieve better correlation than VMAF and P.1204.3. It can extrapolate to different dynamic ranges, and is suitable for real-time video quality metrics delivery in the bitstream. The performance is verified by in-distribution and cross-dataset tests. This work paves the way for adaptive client-side heuristics, real-time segment optimization, dynamic bitrate capping, and quality-dependent post-processing neural network switching, etc.
We propose a framework for learned image and video compression using the generative sparse visual representation (SVR) guided by fidelity-preserving controls. By embedding inputs into a discrete latent space spanned by learned visual codebooks, SVR-based compression transmits integer codeword indices, which is efficient and cross-platform robust. However, high-quality (HQ) reconstruction in the decoder relies on intermediate feature inputs from the encoder via direct connections. Due to the prohibitively high transmission costs, previous SVR-based compression methods remove such feature links, resulting in largely degraded reconstruction quality. In this work, we treat the intermediate features as fidelity-preserving control signals that guide the conditioned generative reconstruction in the decoder. Instead of discarding or directly transferring such signals, we draw them from a low-quality (LQ) fidelity-preserving alternative input that is sent to the decoder with very low bitrate. These control signals provide complementary fidelity cues to improve reconstruction, and their quality is determined by the compression rate of the LQ alternative, which can be tuned to trade off bitrate, fidelity and perceptual quality. Our framework can be conveniently used for both learned image compression (LIC) and learned video compression (LVC). Since SVR is robust against input perturbations, a large portion of codeword indices between adjacent frames can be the same. By only transferring different indices, SVR-based LIC and LVC can share a similar processing pipeline. Experiments over standard image and video compression benchmarks demonstrate the effectiveness of our approach.
Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task, mandating a dedicated decoder per task. In contrast, traditional video codecs employ a flexible encoder controller, enabling the adaptation of a single codec to different tasks through mechanisms like mode prediction. Drawing inspiration from this, we introduce an innovative encoder controller for deep video compression for machines. This controller features a mode prediction and a Group of Pictures (GoP) selection module. Our approach centralizes control at the encoding stage, allowing for adaptable encoder adjustments across different tasks, such as detection and tracking, while maintaining compatibility with a standard pre-trained DVC decoder. Empirical evidence demonstrates that our method is applicable across multiple tasks with various existing pre-trained DVCs. Moreover, extensive experiments demonstrate that our method outperforms previous DVC by about 25% bitrate for different tasks, with only one pre-trained decoder.
Deep learning-based video compression is a challenging task, and many previous state-of-the-art learning-based video codecs use optical flows to exploit the temporal correlation between successive frames and then compress the residual error. Although these two-stage models are end-to-end optimized, the epistemic uncertainty in the motion estimation and the aleatoric uncertainty from the quantization operation lead to errors in the intermediate representations and introduce artifacts in the reconstructed frames. This inherent flaw limits the potential for higher bit rate savings. To address this issue, we propose an uncertainty-aware video compression model that can effectively capture the predictive uncertainty with deep ensembles. Additionally, we introduce an ensemble-aware loss to encourage the diversity among ensemble members and investigate the benefits of incorporating adversarial training in the video compression task. Experimental results on 1080p sequences show that our model can effectively save bits by more than 20% compared to DVC Pro.
The rise of new video modalities like virtual reality or autonomous driving has increased the demand for efficient multi-view video compression methods, both in terms of rate-distortion (R-D) performance and in terms of delay and runtime. While most recent stereo video compression approaches have shown promising performance, they compress left and right views sequentially, leading to poor parallelization and runtime performance. This work presents Low-Latency neural codec for Stereo video Streaming (LLSS), a novel parallel stereo video coding method designed for fast and efficient low-latency stereo video streaming. Instead of using a sequential cross-view motion compensation like existing methods, LLSS introduces a bidirectional feature shifting module to directly exploit mutual information among views and encode them effectively with a joint cross-view prior model for entropy coding. Thanks to this design, LLSS processes left and right views in parallel, minimizing latency; all while substantially improving R-D performance compared to both existing neural and conventional codecs.
Autonomous driving systems require extensive data collection schemes to cover the diverse scenarios needed for building a robust and safe system. The data volumes are in the order of Exabytes and have to be stored for a long period of time (i.e., more than 10 years of the vehicle's life cycle). Lossless compression doesn't provide sufficient compression ratios, hence, lossy video compression has been explored. It is essential to prove that lossy video compression artifacts do not impact the performance of the perception algorithms. However, there is limited work in this area to provide a solid conclusion. In particular, there is no such work for fisheye cameras, which have high radial distortion and where compression may have higher artifacts. Fisheye cameras are commonly used in automotive systems for 3D object detection task. In this work, we provide the first analysis of the impact of standard video compression codecs on wide FOV fisheye camera images. We demonstrate that the achievable compression with negligible impact depends on the dataset and temporal prediction of the video codec. We propose a radial distortion-aware zonal metric to evaluate the performance of artifacts in fisheye images. In addition, we present a novel method for estimating affine mode parameters of the latest VVC codec, and suggest some areas for improvement in video codecs for the application to fisheye imagery.
Implicit neural representations (INR) excel in encoding videos within neural networks, showcasing promise in computer vision tasks like video compression and denoising. INR-based approaches reconstruct video frames from content-agnostic embeddings, which hampers their efficacy in video frame regression and restricts their generalization ability for video interpolation. To address these deficiencies, Hybrid Neural Representation for Videos (HNeRV) was introduced with content-adaptive embeddings. Nevertheless, HNeRV's compression ratios remain relatively low, attributable to an oversight in leveraging the network's shallow features and inter-frame residual information. In this work, we introduce an advanced U-shaped architecture, Vector Quantized-NeRV (VQ-NeRV), which integrates a novel component--the VQ-NeRV Block. This block incorporates a codebook mechanism to discretize the network's shallow residual features and inter-frame residual information effectively. This approach proves particularly advantageous in video compression, as it results in smaller size compared to quantized features. Furthermore, we introduce an original codebook optimization technique, termed shallow codebook optimization, designed to refine the utility and efficiency of the codebook. The experimental evaluations indicate that VQ-NeRV outperforms HNeRV on video regression tasks, delivering superior reconstruction quality (with an increase of 1-2 dB in Peak Signal-to-Noise Ratio (PSNR)), better bit per pixel (bpp) efficiency, and improved video inpainting outcomes.
The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video compression, and major efforts have been dedicated to improving its compression efficiency. However, most proposed works target compression efficiency by employing more complex DNNS, which contributes to higher computational complexity. Alternatively, this paper proposes to improve compression by fully exploiting the existing DNN capacity. To do so, the latent features are guided to learn a richer and more diverse set of features, which corresponds to better reconstruction. A channel-wise feature decorrelation loss is designed and is integrated into the LC optimization. Three strategies are proposed and evaluated, which optimize (1) the transformation network, (2) the context model, and (3) both networks. Experimental results on two established LC methods show that the proposed method improves the compression with a BD-Rate of up to 8.06%, with no added complexity. The proposed solution can be applied as a plug-and-play solution to optimize any similar LC method.
Video compression artifacts arise due to the quantization operation in the frequency domain. The goal of video quality enhancement is to reduce compression artifacts and reconstruct a visually-pleasant result. In this work, we propose a hierarchical frequency-based upsampling and refining neural network (HFUR) for compressed video quality enhancement. HFUR consists of two modules: implicit frequency upsampling module (ImpFreqUp) and hierarchical and iterative refinement module (HIR). ImpFreqUp exploits DCT-domain prior derived through implicit DCT transform, and accurately reconstructs the DCT-domain loss via a coarse-to-fine transfer. Consequently, HIR is introduced to facilitate cross-collaboration and information compensation between the scales, thus further refine the feature maps and promote the visual quality of the final output. We demonstrate the effectiveness of the proposed modules via ablation experiments and visualized results. Extensive experiments on public benchmarks show that HFUR achieves state-of-the-art performance for both constant bit rate and constant QP modes.