Sparsity Invariant CNNs

August 22, 2017 Β· Declared Dead Β· πŸ› International Conference on 3D Vision

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jonas Uhrig, Nick Schneider, Lukas Schneider, Uwe Franke, Thomas Brox, Andreas Geiger arXiv ID 1708.06500 Category cs.CV: Computer Vision Citations 912 Venue International Conference on 3D Vision Last Checked 4 months ago
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 with respect to 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 and will be made available upon publication.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Computer Vision

πŸŒ… πŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV πŸ› ICCV πŸ“š 27.7K cites 11 years ago

Died the same way β€” πŸ‘» Ghosted