Pith. sign in

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

arxiv 1708.06500 v2 pith:UJHNHGH6 submitted 2017-08-22 cs.CV

classification cs.CV
keywords datasparsedepthconvolutionnetworkconvolutionaldatasetinvariant
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing self-supervised monocular depth estimation with traditional visual odometry

    cs.CV 2019-08 conditional novelty 6.0 of 10

    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.

  2. Image-Guided Depth Sampling and Reconstruction

    cs.CV 2019-08 conditional novelty 6.0 of 10

    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.

Pith tools