In this paper, we study a new problem arising from the emerging MPEG standardization effort Video Coding for Machine (VCM), which aims to bridge the gap between visual feature compression and classical video coding. VCM is committed to address the requirement of compact signal representation for both machine and human vision in a more or less scalable way. To this end, we make endeavors in leveraging the strength of predictive and generative models to support advanced compression techniques for both machine and human vision tasks simultaneously, in which visual features serve as a bridge to connect signal-level and task-level compact representations in a scalable manner. Specifically, we employ a conditional deep generation network to reconstruct video frames with the guidance of learned motion pattern. By learning to extract sparse motion pattern via a predictive model, the network elegantly leverages the feature representation to generate the appearance of to-be-coded frames via a generative model, relying on the appearance of the coded key frames. Meanwhile, the sparse motion pattern is compact and highly effective for high-level vision tasks, e.g. action recognition. Experimental results demonstrate that our method yields much better reconstruction quality compared with the traditional video codecs (0.0063 gain in SSIM), as well as state-of-the-art action recognition performance over highly compressed videos (9.4% gain in recognition accuracy), which showcases a promising paradigm of coding signal for both human and machine vision.
DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines
National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台）；Department of Computing and Decision Sciences, Lingnan University（岭南大学计算与决策科学系）
Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application
School of Electronics and Communication Engineering, Shenzhen Campus, Sun Yat-Sen University（中山大学深圳校区电子与通信工程学院）；National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Video and image coding for machines (VCM) is an emerging field that aims to develop compression methods resulting in optimal bitstreams when the decoded frames are analyzed by a neural network. Several approaches already exist improving classic hybrid codecs for this task. However, neural compression networks (NCNs) have made an enormous progress in coding images over the last years. Thus, it is reasonable to consider such NCNs, when the information sink at the decoder side is a neural network as well. Therefore, we build-up an evaluation framework analyzing the performance of four state-of-th…
Symmetric Entropy-Constrained Video Coding for Machines
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；School of Computer and Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；China-Singapore International Joint Research Institute (CSIJRI)（中新国际联合研究院）；Laboratoire des Signaux et Systèmes, Université Paris-Saclay, CNRS, CentraleSupelec（巴黎萨克雷大学信号与系统实验室）
Cross-component linear model (CCLM) prediction has been repeatedly proven to be effective in reducing the inter-channel redundancies in video compression. Essentially speaking, the linear model is identically trained by employing accessible luma and chroma reference samples at both encoder and decoder, elevating the level of operational complexity due to the least square regression or max-min based model parameter derivation. In this paper, we investigate the capability of the linear model in the context of sub-sampled based cross-component correlation mining, as a means of significantly relea…
Video coding technology has been continuously improved for higher compression ratio with higher resolution. However, the state-of-the-art video coding standards, such as H.265/HEVC and Versatile Video Coding, are still designed with the assumption the compressed video will be watched by humans. With the tremendous advance and maturation of deep neural networks in solving computer vision tasks, more and more videos are directly analyzed by deep neural networks without humans' involvement. Such a conventional design for video coding standard is not optimal when the compressed video is used by co…
Conceptual coding has been an emerging research topic recently, which encodes natural images into disentangled conceptual representations for compression. However, the compression performance of the existing methods is still sub-optimal due to the lack of comprehensive consideration of rate constraint and reconstruction quality. To this end, we propose a novel end-to-end semantic prior modeling-based conceptual coding scheme towards extremely low bitrate image compression, which leverages semantic-wise deep representations as a unified prior for entropy estimation and texture synthesis. Specif…
In the emerging field of video coding for machines, video datasets with pristine video quality and high-quality annotations are required for a comprehensive evaluation. However, existing video datasets with detailed annotations are severely limited in size and video quality. Thus, current methods have to either evaluate their codecs on still images or on already compressed data. To mitigate this problem, we propose an evaluation method based on pseudo ground-truth data from the field of semantic segmentation to the evaluation of video coding for machines. Through extensive evaluation, this pap…
Aerial surveillance from Unmanned Aerial Vehicles (UAVs), i.e. with moving cameras, is of growing interest for police as well as disaster area monitoring. For more detailed ground images the camera resolutions are steadily increasing. Simultaneously the amount of video data to transmit is increasing significantly, too. To reduce the amount of data, Region of Interest (ROI) coding systems were introduced which mainly encode some regions in higher quality at the cost of the remaining image regions. We employ an existing ROI coding system relying on global motion compensation to retain full image…
For any video codecs, the coding efficiency highly relies on whether the current signal to be encoded can find the relevant contexts from the previous reconstructed signals. Traditional codec has verified more contexts bring substantial coding gain, but in a time-consuming manner. However, for the emerging neural video codec (NVC), its contexts are still limited, leading to low compression ratio. To boost NVC, this paper proposes increasing the context diversity in both temporal and spatial dimensions. First, we guide the model to learn hierarchical quality patterns across frames, which enrich…
With the growing data consumption of emerging video applications and users requirement for higher resolutions, up to 8K, a huge effort has been made in video compression technologies. Recently, versatile video coding (VVC) has been standardized by the moving picture expert group (MPEG), providing a significant improvement in compression performance over its predecessor high efficiency video coding (HEVC). In this paper, we provide a comparative subjective quality evaluation between VVC and HEVC standards for 8K resolution videos. In addition, we evaluate the perceived quality improvement offer…
