B
Benjamin Ummenhofer
Researcher at Intel
Publications - 20
Citations - 1690
Benjamin Ummenhofer is an academic researcher from Intel. The author has contributed to research in topics: 3D reconstruction & Computer science. The author has an hindex of 10, co-authored 17 publications receiving 1302 citations. Previous affiliations of Benjamin Ummenhofer include University of Freiburg.
Papers
More filters
Proceedings ArticleDOI
DeMoN: Depth and Motion Network for Learning Monocular Stereo
Benjamin Ummenhofer,Huizhong Zhou,Jonas Uhrig,Nikolaus Mayer,Eddy Ilg,Alexey Dosovitskiy,Thomas Brox +6 more
TL;DR: DeMoN as mentioned in this paper proposes an end-to-end architecture composed of multiple stacked encoder-decoder networks, the core part being an iterative network that is able to improve its own predictions.
Proceedings ArticleDOI
DeMoN: Depth and Motion Network for Learning Monocular Stereo
Benjamin Ummenhofer,Huizhong Zhou,Jonas Uhrig,Nikolaus Mayer,Eddy Ilg,Alexey Dosovitskiy,Thomas Brox +6 more
TL;DR: This work trains a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs, and in contrast to the popular depth-from-single-image networks, DeMoN learns the concept of matching and better generalizes to structures not seen during training.
Book ChapterDOI
DeepTAM: Deep Tracking and Mapping
TL;DR: This work presents a system for keyframe-based dense camera tracking and depth map estimation that is entirely learned, and shows that generating a large number of pose hypotheses leads to more accurate predictions.
Proceedings Article
Lagrangian Fluid Simulation with Continuous Convolutions
TL;DR: This work presents an approach to Lagrangian fluid simulation with a new type of convolutional network that can simulate different materials, generalizes to arbitrary collision geometries, and can be used for inverse problems.
Proceedings ArticleDOI
CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
TL;DR: In this article, a new type of convolution is proposed to take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns, which improves the generalization capabilities of depth prediction networks considerably.