mlsanityData to 14 Oct 2026

Fast Sparse 3D Convolution Network with VDB

arXiv 2311.02762 ↗First posted 5 Nov 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We proposed a new Convolution Neural Network implementation optimized for sparse 3D data inference. This implementation uses NanoVDB as the data structure to store the sparse tensor. It leaves a relatively small memory footprint while maintaining high performance. We demonstrate that this architecture is around 20 times faster than the state-of-the-art dense CNN model on a high-resolution 3D object classification network.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 9 references that are in the map. First posted on arXiv 5 Nov 2023.

Builds on

5 of 9 references.

References · 5

  1. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  3. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  4. 2015Sparse 3D convolutional neural networkscited by 72
  5. 2022Learning strides in convolutional neural networkscited by 26

Built on by

Not cited yet.