A Multi-Scale Guided Cascade Hourglass Network for Depth Completion

Ang Li, Zejian Yuan, Yonggen Ling, Wanchao Chi, shenghao zhang, Chong Zhang; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 32-40

Abstract


Depth completion, a task to estimate the dense depth map from sparse measurement under the guidance from the high-resolution image, is essential to many computer vision applications. Most previous methods building on fully convolutional networks can not handle diverse patterns in the depth map efficiently and effectively. We propose a multi-scale guided cascade hourglass network to tackle this problem. Structures at different levels are captured by specialized hourglasses in the cascade network with sparse inputs in various sizes. An encoder extracts multiscale features from color image to provide deep guidance for all the hourglasses. A multi-scale training strategy further activates the effect of cascade stages. With the role of each sub-module divided explicitly, we can implement components with simple architectures. Extensive experiments show that our lightweight model achieves competitive results compared with state-of-the-art in KITTI depth completion benchmark, with low complexity in run-time.

Related Material


[pdf]
[bibtex]
@InProceedings{Li_2020_WACV,
author = {Li, Ang and Yuan, Zejian and Ling, Yonggen and Chi, Wanchao and zhang, shenghao and Zhang, Chong},
title = {A Multi-Scale Guided Cascade Hourglass Network for Depth Completion},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}