Scalable Face Image Coding via StyleGAN Prior: Toward Compression for Human-Machine Collaborative Vision.

The accelerated proliferation of visual content and the rapid development of machine vision technologies bring significant challenges in delivering visual data on a gigantic scale, which shall be effectively represented to satisfy both human and machine requirements. In this work, we investigate how hierarchical representations derived from the advanced generative prior facilitate constructing an efficient scalable coding paradigm for human-machine collaborative vision. Our key insight is that by exploiting the StyleGAN prior, we can learn three-layered representations encoding hierarchical semantics, which are elaborately designed into the basic, middle, and enhanced layers, supporting machine intelligence and human visual perception in a progressive fashion. With the aim of achieving efficient compression, we propose the layer-wise scalable entropy transformer to reduce the redundancy between layers. Based on the multi-task scalable rate-distortion objective, the proposed scheme is jointly optimized to achieve optimal machine analysis performance, human perception experience, and compression ratio. We validate the proposed paradigm's feasibility in face image compression. Extensive qualitative and quantitative experimental results demonstrate the superiority of the proposed paradigm over the latest compression standard Versatile Video Coding (VVC) in terms of both machine analysis as well as human perception at extremely low bitrates (< 0.01 bpp), offering new insights for human-machine collaborative compression.

Multiservice-Based Traffic Scheduling for 5G Access Traffic Steering, Switching and Splitting.

As a key enabler of the access traffic steering, switching and splitting (ATSSS) feature, multipath transport can leverage the simultaneous use of several network paths and support seamless failover to improve both communication throughput and resilience. Therefore, a traffic scheduling strategy is necessary to determine the best network path combination that may improve the performance of multipath transport. To address this need, we developed a multiservice-type based transmission (MSTT) traffic scheduling optimization strategy, which involves three steps. First, the user equipment (UE) selects the number of data stream transmission paths, considering the service utility function, and either transmits all data streams via the 3GPP network or sends two streams, one via the 3GPP network and the other via the non-3GPP network. Second, the proposed method is used to select the transmission path for each data stream based on load balancing. Finally, an algorithm for optimizing traffic scheduling is formulated by applying the convex optimization problem to maximize the effective network capacity under a Delay Quality of Service (DQoS) constraint. The proposed traffic scheduling strategy is validated through simulation experiments. The results indicate that user satisfaction and effective capacity realized are always better than when using the always-best-connected and fixed-ratio power-allocation algorithms.

Salient Region Guided Blind Image Sharpness Assessment.

Salient regions provide important cues for scene understanding to the human vision system. However, whether the detected salient regions are helpful in image blur estimation is unknown. In this study, a salient region guided blind image sharpness assessment (BISA) framework is proposed, and the effect of the detected salient regions on the BISA performance is investigated. Specifically, three salient region detection (SRD) methods and ten BISA models are jointly explored, during which the output saliency maps from SRD methods are re-organized as the input of BISA models. Consequently, the change in BISA metric values can be quantified and then directly related to the difference in BISA model inputs. Finally, experiments are conducted on three Gaussian blurring image databases, and the BISA prediction performance is evaluated. The comparison results indicate that salient region input can help achieve a close and sometimes superior performance to a BISA model over the whole image input. When using the center region input as the baseline, the detected salient regions from the saliency optimization from robust background detection (SORBD) method lead to consistently better score prediction, regardless of the BISA model. Based on the proposed hybrid framework, this study reveals that saliency detection benefits image blur estimation, while how to properly incorporate SRD methods and BISA models to improve the score prediction will be explored in our future work.