Saved in:
Bibliographic Details
Main Authors: Chang, Qiong, Li, Xiang, Xu, Xin, Liu, Xin, Li, Yun, Jun, Miyazaki
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.11566
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908400644784128
author Chang, Qiong
Li, Xiang
Xu, Xin
Liu, Xin
Li, Yun
Jun, Miyazaki
author_facet Chang, Qiong
Li, Xiang
Xu, Xin
Liu, Xin
Li, Yun
Jun, Miyazaki
contents We present a lightweight system for stereo matching through embedded GPUs. It breaks the trade-off between accuracy and processing speed in stereo matching, enabling our embedded system to further improve the matching accuracy while ensuring real-time processing. The main idea of our method is to construct a tiny neural network based on variational auto-encoder (VAE) to upsample and refinement a small size of coarse disparity map, which is first generated by a traditional matching method. The proposed hybrid structure cannot only bring the advantage of traditional methods in terms of computational complexity, but also ensure the matching accuracy under the impact of neural network. Extensive experiments on the KITTI 2015 benchmark demonstrate that our tiny system exhibits high robustness in improving the accuracy of the coarse disparity maps generated by different algorithms, while also running in real-time on embedded GPUs.
format Preprint
id arxiv_https___arxiv_org_abs_2305_11566
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle StereoVAE: A lightweight stereo-matching system using embedded GPUs
Chang, Qiong
Li, Xiang
Xu, Xin
Liu, Xin
Li, Yun
Jun, Miyazaki
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
Robotics
We present a lightweight system for stereo matching through embedded GPUs. It breaks the trade-off between accuracy and processing speed in stereo matching, enabling our embedded system to further improve the matching accuracy while ensuring real-time processing. The main idea of our method is to construct a tiny neural network based on variational auto-encoder (VAE) to upsample and refinement a small size of coarse disparity map, which is first generated by a traditional matching method. The proposed hybrid structure cannot only bring the advantage of traditional methods in terms of computational complexity, but also ensure the matching accuracy under the impact of neural network. Extensive experiments on the KITTI 2015 benchmark demonstrate that our tiny system exhibits high robustness in improving the accuracy of the coarse disparity maps generated by different algorithms, while also running in real-time on embedded GPUs.
title StereoVAE: A lightweight stereo-matching system using embedded GPUs
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
Robotics
url https://arxiv.org/abs/2305.11566