% Keywords: Bit Rate
% Encoding: utf-8
@InProceedings{Zabrovskiy2021c,
  author = {Anatoliy Zabrovskiy and Prateek Agrawal and Christian Timmerer and Radu Prodan},
  booktitle = {2021 30th Conference of Open Innovations Association (FRUCT)},
  title = {{FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machine Learning}},
  year = {2021},
  month = {oct},
  pages = {292--302},
  publisher = {IEEE},
  abstract = {HTTP adaptive video streaming is a widespread and sought-after technology on the Internet that allows clients to dynamically switch between different stream qualities presented in the bitrate ladder to optimize overall received video quality. Currently, there exist several approaches of different complexity for building such a ladder. The simplest method is to use a static bitrate ladder, and the more complex one is to compute a per-title encoding ladder. The main drawback of these approaches is that they do not provide bitrate ladders for scenes with different visual complexity within the video. Moreover, most modern methods require additional computationally-intensive test encodings of the entire video to construct the convex hull, used to calculate the bitrate ladder. This paper proposes a new fast per-scene encoding approach called FAUST based on 1) quick entropy-based scene detection and 2) prediction of optimized bitrate ladder for each scene using an artificial neural network. The results show that our model reduces the mean absolute error to 0.15, the mean square error to 0.08, and the bitrate to 13.5 % while increasing the difference in video multimethod assessment fusion to 5.6 points.},
  doi = {10.23919/fruct53335.2021.9599963},
  keywords = {Visualization, Technological innovation, Bit rate, Switches, Mean square error methods, Streaming media, Encoding},
  url = {https://ieeexplore.ieee.org/document/9599963}
}
@InProceedings{Amirpour2021a,
  author = {Hadi Amirpour and Hannaneh Barahouei Pasandi and Christian Timmerer and Mohammad Ghanbari},
  booktitle = {2021 International Conference on Visual Communications and Image Processing (VCIP)},
  title = {{Improving Per-title Encoding for HTTP Adaptive Streaming by Utilizing Video Super-resolution}},
  year = {2021},
  month = {dec},
  pages = {1--5},
  publisher = {IEEE},
  abstract = {In per-title encoding, to optimize a bitrate ladder over spatial resolution, each video segment is downscaled to a set of spatial resolutions, and they are all encoded at a given set of bitrates. To find the highest quality resolution for each bitrate, the low-resolution encoded videos are upscaled to the original resolution, and a convex hull is formed based on the scaled qualities. Deep learning-based video super-resolution (VSR) approaches show a significant gain over traditional upscaling approaches, and they are becoming more and more efficient over time. This paper improves the per-title encoding over the upscaling methods by using deep neural network-based VSR algorithms. Utilizing a VSR algorithm by improving the quality of low-resolution encodings can improve the convex hull. As a result, it will lead to an improved bitrate ladder. To avoid bandwidth wastage at perceptually lossless bitrates, a maximum threshold for the quality is set, and encodings beyond it are eliminated from the bitrate ladder. Similarly, a minimum threshold is set to avoid low-quality video delivery. The encodings between the maximum and minimum thresholds are selected based on one Just Noticeable Difference. Our experimental results show that the proposed per-title encoding results in a 24% bitrate reduction and 53% storage reduction compared to the state-of-the-art method.},
  doi = {10.1109/vcip53242.2021.9675403},
  keywords = {Image coding, Visual communication, Bit rate, Superresolution, Bandwidth, Streaming media, Spatial resolution, HAS, per-title, deep learning, compression, bitrate ladder},
  url = {https://ieeexplore.ieee.org/document/9675403}
}
@Article{Hooft2020a,
  author = {Jeroen van der Hooft and Maria Torres Vega and Tim Wauters and Christian Timmerer and Ali C. Begen and Filip De Turck and Raimund Schatz},
  journal = {IEEE Communications Magazine},
  title = {{From Capturing to Rendering: Volumetric Media Delivery with Six Degrees of Freedom}},
  year = {2020},
  issn = {0163-6804},
  month = {oct},
  number = {10},
  pages = {49--55},
  volume = {58},
  abstract = {Technological improvements are rapidly advancing holographic-type content distribution. Significant research efforts have been made to meet the low-latency and high-bandwidth requirements set forward by interactive applications such as remote surgery and virtual reality. Recent research made six degrees of freedom (6DoF) for immersive media possible, where users may both move their heads and change their position within a scene. In this article, we present the status and challenges of 6DoF applications based on volumetric media, focusing on the key aspects required to deliver such services. Furthermore, we present results from a subjective study to highlight relevant directions for future research.},
  doi = {10.1109/mcom.001.2000242},
  keywords = {Streaming media, Media, Cameras, Three-dimensional displays, Encoding, Bit rate, Real-time systems},
  publisher = {Institute of Electrical and Electronics Engineers ({IEEE})},
  url = {https://ieeexplore.ieee.org/document/9247522}
}