SPLATNet: Sparse Lattice Networks for Point Cloud Processing

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naïvely applying convolutions on this lattice scales poorly, both in terms of memory and computational cost, as the si...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 2530 - 2539
Main Authors Su, Hang, Jampani, Varun, Sun, Deqing, Maji, Subhransu, Kalogerakis, Evangelos, Yang, Ming-Hsuan, Kautz, Jan
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Online AccessGet full text

Cover

Loading…