activity
20192021
most citedA Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions

2 citations · 2 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2021

L2PF -- Learning to Prune Faster

Manoj-Rohit Vemparala, Nael Fasfous, Alexander Frickenstein +6

Various applications in the field of autonomous driving are based on convolutional neural networks (CNNs), especially for processing camera data. The optimization of such CNNs is a…

cs.CV2020

MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flow

René Schuster, Christian Unger, Didier Stricker

Contrary to the ongoing trend in automotive applications towards usage of more diverse and more sensors, this work tries to solve the complex scene flow problem under a monocular c…

cs.CV20202 cited

A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions

René Schuster, Christian Unger, Didier Stricker

Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in…

cs.CV2020

SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation

René Schuster, Oliver Wasenmüller, Christian Unger +1

Interpolation of sparse pixel information towards a dense target resolution finds its application across multiple disciplines in computer vision. State-of-the-art interpolation of…

cs.CV2020

Binary DAD-Net: Binarized Driveable Area Detection Network for Autonomous Driving

Alexander Frickenstein, Manoj Rohit Vemparala, Jakob Mayr +4

Driveable area detection is a key component for various applications in the field of autonomous driving (AD), such as ground-plane detection, obstacle detection and maneuver planni…

cs.CV2019

An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching

René Schuster, Oliver Wasenmüller, Christian Unger +1

Training a deep neural network is a non-trivial task. Not only the tuning of hyperparameters, but also the gathering and selection of training data, the design of the loss function…