H
Hayko Riemenschneider
Researcher at ETH Zurich
Publications - 44
Citations - 1902
Hayko Riemenschneider is an academic researcher from ETH Zurich. The author has contributed to research in topics: Point cloud & Automatic summarization. The author has an hindex of 18, co-authored 44 publications receiving 1641 citations. Previous affiliations of Hayko Riemenschneider include Graz University of Technology & Microsoft.
Papers
More filters
Book ChapterDOI
Creating Summaries from User Videos
TL;DR: This paper proposes a novel approach and a new benchmark for video summarization, which focuses on user videos, which are raw videos containing a set of interesting events, and generates high-quality results, comparable to manual, human-created summaries.
Proceedings ArticleDOI
The Interestingness of Images
TL;DR: This work introduces a set of features computationally capturing the three main aspects of visual interestingness and builds an interestingness predictor from them, shown on three datasets with varying context, reflecting the prior knowledge of the viewers.
Proceedings ArticleDOI
3D all the way: Semantic segmentation of urban scenes from start to end in 3D
TL;DR: It is shown that a properly trained pure-3D approach produces high quality labelings, with significant speed benefits allowing us to analyze entire streets in a matter of minutes, and a novel facade separation based on semantic nuances between facades is proposed.
Proceedings ArticleDOI
Irregular lattices for complex shape grammar facade parsing
Hayko Riemenschneider,Ulrich Krispel,Wolfgang Thaller,Michael Donoser,Sven Havemann,Dieter W. Fellner,Horst Bischof +6 more
TL;DR: This work provides feasible generic facade reconstruction by combining low-level classifiers with mid-level object detectors to infer an irregular lattice, which preserves the logical structure of the facade while reducing the search space to a manageable size.
Book ChapterDOI
Learning Where to Classify in Multi-view Semantic Segmentation
TL;DR: In this paper, the geometry of a 3D mesh model obtained from multi-view reconstruction is exploited to predict the best view before the actual labeling, which leads to a further reduction of computation time and a gain in accuracy.