REVIEW 2 cited by
Sparsity Invariant CNNs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original 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.
Forward citations
Cited by 2 Pith papers
-
Enhancing self-supervised monocular depth estimation with traditional visual odometry
A sparse autoencoder densifies visual odometry points and feeds them as a geometric prior to self-supervised monocular depth networks, improving depth accuracy on KITTI.
-
Image-Guided Depth Sampling and Reconstruction
An RGB-superpixel-guided depth sampling and reconstruction method with one sample per segment plus bilateral filtering outperforms random and grid sampling on indoor and outdoor benchmarks.
Discussion (0). Continue with ORCID to comment.