.png){kind=icon}
返回
Self-supervised learning of monocular depth using quantized networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2021.11.071.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Learning monocular depth in a self-supervised manner is desirable for numerous applications ranging from autonomous driving, robotics to augmented reality. However, the current challenges lie in the problems of scale ambiguity, dynamic scene and hardware limitations. To this end, a self-supervised approach is proposed in this work for monocular depth learning and estimation. Specifically, we first introduce a self-supervised depth learning framework that learns a part of the camera intrinsics and the stereo extrinsics, which ensures the absoluteness of the predicted depth while achieving enhanced performance (i.e., lower error between the predicted depth and the ground-truth) on depth estimation. Besides, we further improve the accuracy and the efficiency (i.e., shorter inference time and lower weight/activation footprints) via a specially-designed network that exploits multi-scale context across multi-level feature maps. In addition, we propose a quantization scheme for our depth estimation networks. The scheme allows the network inference to be carried out using INT4-INT8 arithmetic while keeping a high performance on depth estimation. Extensive experiments on KITTI and Make3D datasets demonstrate that our approach substantially boosts the performance compared to the existing state-of-the-art methods on monocular depth estimation. (C) 2021 Elsevier B.V. All rights reserved.
Keyword:
Monocular depth estimation
Absolute scale
Self-supervised learning
Quantized depth networks
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Self-supervised monocular image depth learning and confidence estimation自监督单目图像深度学习和置信度估计.png)
NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Robot teaching by teleoperation based on visual interaction and extreme learning machineNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏 没有更多内容
没有更多内容