Alexander Dvorkovich

Aleksandr Ivchenko, Pavel Kononyuk, Alexander Dvorkovich et al.

Dynamic adaptive streaming over HTTP provides the work of most multimedia services, however, the nature of this technology further complicates the assessment of the QoE (Quality of Experience). In this paper, the influence of various objective factors on the subjective estimation of the QoE of streaming video is studied. The paper presents standard and handcrafted features, shows their correlation and p-Value of significance. VQA (Video Quality Assessment) models based on regression and gradient boosting with SRCC reaching up to 0.9647 on the validation subsample are proposed. The proposed regression models are adapted for applied applications (both with and without a reference video); the Gradient Boosting Regressor model is perspective for further improvement of the quality estimation model. We take SQoE-III database, so far the largest and most realistic of its kind. The VQA (video quality assessment) models are available at https://github.com/AleksandrIvchenko/QoE-assesment

Chuang-Wei Liu, Mingjian Sun, Cairong Zhao et al.

Unsupervised stereo matching has garnered significant attention for its independence from costly disparity annotations. Typical unsupervised methods rely on the multi-view consistency assumption for training networks, which suffer considerably from stereo matching ambiguities, such as repetitive patterns and texture-less regions. A feasible solution lies in transferring 3D geometric knowledge from a relative depth map to the stereo matching networks. However, existing knowledge transfer methods learn depth ranking information from randomly built sparse correspondences, which makes inefficient utilization of 3D geometric knowledge and introduces noise from mistaken disparity estimates. This work proposes a novel unsupervised learning framework to address these challenges, which comprises a plug-and-play disparity confidence estimation algorithm and two depth prior-guided loss functions. Specifically, the local coherence consistency between neighboring disparities and their corresponding relative depths is first checked to obtain disparity confidence. Afterwards, quasi-dense correspondences are built using only confident disparity estimates to facilitate efficient depth ranking learning. Finally, a dual disparity smoothness loss is proposed to boost stereo matching performance at disparity discontinuities. Experimental results demonstrate that our method achieves state-of-the-art stereo matching accuracy on the KITTI Stereo benchmarks among all unsupervised stereo matching methods.