Moving Picture Experts Group (MPEG) is developing a standard for immersive video coding called MPEG Immersive Video (MIV) and is releasing a reference software called Test Model for Immersive Video (TMIV) in the standardization process. The TMIV efficiently compresses an immersive video comprising a set of texture and depth views acquired using multiple cameras within a limited 3D viewing space. Moreover, it affords a rendered view of an arbitrary view position and orientation with six degrees of freedom. However, the existing depth quantization applied to depth atlas in TMIV is insufficient since the reconstructed depth is crucial for achieving the required quality of a rendered viewport. To address this issue, we propose a nonlinear depth quantization method that allocates more codewords to a depth subrange with a higher occurrence of depth values located at edge regions, which are important in terms of the rendered view quality. We implement the proposed nonlinear quantization based on piecewise linear scaling considering the computational complexity and bitstream overhead. The experimental results show that the proposed method yields PSNR-based Bjøntegaard delta rate gains of 5.2% and 4.9% in the end-to-end performance for High- and Low-bitrate ranges, respectively. Moreover, subjective quality improvement is mainly observed at the object boundaries of the rendered viewport. The proposed nonlinear quantization method has been adopted into the TMIV as a candidate standard technology for the next MIV edition.

Convolutional neural network-based single image super-resolution (SISR) involves numerous parameters and high computational expenses to ensure improved performance, limiting its applicability in resource-constrained devices such as mobile phones. Knowledge distillation (KD), which transfers useful knowledge from a teacher network to a student network, has been investigated as a method to make networks more efficient in terms of performance. To this end, feature distillation (FD) has been utilized in KD to minimize the Euclidean distance-based loss of feature maps between teacher and student networks. However, this technique does not adequately consider the effective and meaningful delivery of knowledge from the teacher to the student network to improve the latter’s performance under given network capacity constraints. In this study, we propose a feature-domain adaptive contrastive distillation (FACD) method to train lightweight student SISR networks efficiently. We highlight the limitations of existing FD methods in terms of Euclidean distance-based loss, and propose a feature-domain contrastive loss, which causes student networks to learn richer information from the teacher’s representation in the feature domain. We also implement adaptive distillation that performs distillation selectively depending on the conditions of the training patches. Experimental results showed that the proposed FACD scheme improves student enhanced deep residual networks and residual channel attention networks not only in terms of the peak signal-to-noise ratio on all benchmark datasets and scales but also in terms of subjective image quality, compared to the conventional FD approaches. Code will be release at https://github.com/hcmoon0613/FACD.

In this paper, a test bed of QoS-aware ubiquitous content access (UCA), which allows a user to access and consume multimedia content through convergent networks of broadcasting and communications (WLAN/CDMA) using diverse devices in a seamless and transparent way, is designed and implemented based on the adaptation of scalable and non-scalable content. Especially, the MPEG-21 digital item adaptation (DIA) is employed to find a systematic solution in choosing an optimal adaptation operation under given usage environments in an interoperable way. Furthermore, scalable video coding (SVC) technology is adopted to provide flexible adaptation in spatial, temporal, and quality dimensions in real-time

Machine vision-based intelligent applications that analyze video data collected by machines are rapidly increasing. Therefore, it is essential to efficiently compress a large volume of video data for machine consumption. Accordingly, the Moving Picture Experts Group (MPEG) has been developing a new video coding standard called Video Coding for Machines (VCM), aimed at video consumed by machines rather than humans. Recently, studies have demonstrated that multi-scale feature compression (MSFC)-based feature compression methods significantly improve the performance of MPEG-VCM. This paper proposes an efficient MSFC (eMSFC) method with quantization parameter (QP)-adaptive feature channel truncation. The proposed eMSFC incorporates an MSFC network with a selective learning strategy (SLS) and Versatile Video Coding (VVC)-based compression. The SLS extracts a single-scale feature from the input image, arranged in order of channel-wise importance. The size of the single-scale feature is adaptively adjusted by truncating the feature channels according to the QP. The truncated feature is efficiently compressed using VVC. Compared to the VCM feature anchor, the experimental results reveal that the proposed method provides a 98.72%, 98.34%, and 98.04% Bjontegaard delta rate gain for machine vision tasks of instance segmentation, object detection, and object tracking, respectively. The proposed method performed best among the “Call for Evidence” response technologies in MPEG-VCM.