# Sparse 3D convolutional neural networks

Source: [Sparse 3D convolutional neural networks](<https://www.sota2.com/research/paper/68fa62101e209131ce9f726a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:30.720Z

Authors: Ben Graham

Published: 2015-05-12T07:30:22.000Z

## Abstract

We have implemented a convolutional neural network designed for processing sparse three-dimensional input data. The world we live in is three dimensional so there are a large number of potential applications including 3D object recognition and analysis of space-time objects. In the quest for efficiency, we experiment with CNNs on the 2D triangular-lattice and 3D tetrahedral-lattice.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Semantic Segmentation on S3DIS (Area 5 test (Fold #1))](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-s3dis-area-5-test-fold-sharp-1.md>): 3D Semantic Segmentation; S3DIS (Area 5 test (Fold #1)); mIoU: 41.72.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1505.02890>)

[PDF](<https://arxiv.org/pdf/1505.02890.pdf>)