S
Sebastian Bosse
Researcher at Heinrich Hertz Institute
Publications - 59
Citations - 2639
Sebastian Bosse is an academic researcher from Heinrich Hertz Institute. The author has contributed to research in topics: Image quality & Encoder. The author has an hindex of 18, co-authored 59 publications receiving 1982 citations. Previous affiliations of Sebastian Bosse include Fraunhofer Society.
Papers
More filters
Journal ArticleDOI
Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
TL;DR: A deep neural network-based approach to image quality assessment (IQA) that allows for joint learning of local quality and local weights in an unified framework and shows a high ability to generalize between different databases, indicating a high robustness of the learned features.
Journal ArticleDOI
Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
TL;DR: In this article, a deep neural network-based approach to image quality assessment (IQA) is presented, which is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for regression.
Journal ArticleDOI
3D High-Efficiency Video Coding for Multi-View Video and Depth Data
Klaus-Robert Müller,Heiko Schwarz,Detlev Marpe,Christian Bartnik,Sebastian Bosse,Heribert Brust,Tobias Hinz,Haricharan Lakshman,Philipp Merkle,F. H. Rhee,Gerhard Tech,Martin Winken,Thomas Wiegand +12 more
TL;DR: This paper describes an extension of the high efficiency video coding (HEVC) standard for coding of multi-view video and depth data, and develops and integrated a novel encoder control that guarantees that high quality intermediate views can be generated based on the decoded data.
Proceedings ArticleDOI
A deep neural network for image quality assessment
TL;DR: This paper presents a no reference image quality assessment (IQA) method based on a deep convolutional neural network (CNN) that takes unpreprocessed image patches as an input and estimates the quality without employing any domain knowledge.
Journal ArticleDOI
A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment
TL;DR: The Haar wavelet-based perceptual similarity index (HaarPSI) as discussed by the authors was proposed to assess local similarities between two images, as well as the relative importance of image areas.