Header logo is avg

avg ps Thumb sm upper body tiny
Andreas Geiger (Project leader)
Max Planck Research Group Leader
no image
Jonas Uhrig
Image Understanding Group, Daimler AG
no image
Nick Schneider
Image Understanding Group, Daimler AG
no image
Uwe Franke
Image Understanding Group, Daimler AG
no image
Lukas Schneider
Image Understanding Group, Daimler AG
no image
Thomas Brox
Computer Vision Group, University of Freiburg
1 result

2017


Thumb xl jonas teaser
Sparsity Invariant CNNs

Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.

International Conference on 3D Vision (3DV) 2017, International Conference on 3D Vision (3DV), October 2017 (conference)

Abstract
In this paper, we consider convolutional neural networks operating on sparse inputs with an application to depth upsampling from sparse laser scan data. First, we show that traditional convolutional networks perform poorly when applied to sparse data even when the location of missing data is provided to the network. To overcome this problem, we propose a simple yet effective sparse convolution layer which explicitly considers the location of missing data during the convolution operation. We demonstrate the benefits of the proposed network architecture in synthetic and real experiments \wrt various baseline approaches. Compared to dense baselines, the proposed sparse convolution network generalizes well to novel datasets and is invariant to the level of sparsity in the data. For our evaluation, we derive a novel dataset from the KITTI benchmark, comprising 93k depth annotated RGB images. Our dataset allows for training and evaluating depth upsampling and depth prediction techniques in challenging real-world settings.

pdf suppmat Project Page Project Page [BibTex]

2017

pdf suppmat Project Page Project Page [BibTex]