INS-Conv: Incremental Sparse Convolution for Online 3D segmentation
Leyao Liu, Tian Zheng, Yun-Jou Lin, Kai Ni, Lu Fang.
InProceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022.
Introduction
This is the incremental sparse convolution (Ins-Conv) library implemented based on SparseConvNet and Live Semantic 3D Perception for Immersive Augmented Reality. The later describes a more efficient GPU implementation of the original submanifold sparse convolution. Our method supports incremental computing of sparse convolution, including SSC, convolution/deconvolution, BN, IO, and residual structure, etc.
Citing
If you find our code useful, please kindly cite our paper:
@inproceedings{liu2022ins,
title={INS-Conv: Incremental Sparse Convolution for Online 3D Segmentation},
author={Liu, Leyao and Zheng, Tian and Lin, Yun-Jou and Ni, Kai and Fang, Lu},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={18975--18984},
year={2022}
}