Pith. sign in

REVIEW 4 cited by

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1711.10275 v1 pith:B2JDGHOL submitted 2017-11-28 cs.CV

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Benjamin Graham , Martin Engelcke , Laurens van der Maaten This is my paper
classification cs.CV
keywords convolutionaldatanetworkssparsesegmentationsemanticcloudsdense
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convolutional networks. We demonstrate the strong performance of the resulting models, called submanifold sparse convolutional networks (SSCNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmentation competition.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement

    cs.CV 2026-07 conditional novelty 7.0

    Iterative sparse-3D-convolution refinement in a log-depth voxel shell, instead of 2D image-plane refinement, sharply improves fine-detail geometry in monocular point maps and sets state of the art on local fine-detail...

  2. Enhanced Ionization Charge Identification in the Short-Baseline Neutrino Program Neutrino Detectors with Deep Neural Networks

    physics.ins-det 2026-05 conditional novelty 6.0

    A DNN-based region of interest detection method for SBN neutrino detectors outperforms traditional wire-by-wire thresholding in identification accuracy and reconstruction quality while being more robust to performance...

  3. SparsePixels: Efficient Convolution for Sparse Data on FPGAs

    cs.AR 2025-12 conditional novelty 6.0

    A fixed-budget sparse-convolution FPGA framework runs CNNs on <=20 of ~4000 pixels, achieving 0.665 us inference for MicroBooNE with a 73x speedup and ~2% AUC loss.

  4. Enhanced Ionization Charge Identification in the Short-Baseline Neutrino Program Neutrino Detectors with Deep Neural Networks

    physics.ins-det 2026-05 unverdicted novelty 5.0

    DNN ROI detection outperforms traditional wire-by-wire thresholding in identifying ionization signals in SBND and ICARUS detectors and shows greater robustness to performance variations.