L
Lukas Schneider
Researcher at Daimler AG
Publications - 22
Citations - 1157
Lukas Schneider is an academic researcher from Daimler AG. The author has contributed to research in topics: Computer science & Upsampling. The author has an hindex of 10, co-authored 18 publications receiving 785 citations. Previous affiliations of Lukas Schneider include ETH Zurich & Mercedes-Benz.
Papers
More filters
Proceedings ArticleDOI
Sparsity Invariant CNNs
TL;DR: This paper proposes a simple yet effective sparse convolution layer which explicitly considers the location of missing data during the convolution operation, and demonstrates the benefits of the proposed network architecture in synthetic and real experiments with respect to various baseline approaches.
Posted Content
Sparsity Invariant CNNs
TL;DR: In this article, the location of missing data is considered in the convolutional layer of the network and a simple sparse convolution layer is proposed for depth upsampling from sparse laser scan data.
Proceedings ArticleDOI
Semantic Stixels: Depth is not enough
Lukas Schneider,Marius Cordts,Timo Rehfeld,David Pfeiffer,Markus Enzweiler,Uwe Franke,Marc Pollefeys,Stefan Roth +7 more
TL;DR: The results indicate that the joint treatment of both cues on the Semantic Stixel level yields a highly compact environment representation while maintaining an accuracy comparable to the two individual pixel-level input data sources.
Book ChapterDOI
Semantically Guided Depth Upsampling
Nick Schneider,Nick Schneider,Lukas Schneider,Lukas Schneider,Peter Pinggera,Uwe Franke,Marc Pollefeys,Christoph Stiller +7 more
TL;DR: This work presents a novel method for accurate and efficient upsampling of sparse depth data, guided by high-resolution imagery that determines globally consistent solutions and preserves fine details and sharp depth boundaries.
Proceedings ArticleDOI
Slanted Stixels: Representing San Francisco's Steepest Streets.
Daniel Hernandez-Juarez,Lukas Schneider,Antonio Espinosa,Juan Carlos Moure,David Vazquez,Antonio M. López,Uwe Franke,Marc Pollefeys +7 more
TL;DR: This work overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects, and the computational complexity of the Stixel inference algorithm is reduced significantly.