论文标题
LITE-MONO：一种轻巧的CNN和变压器架构，用于自我监视的单眼估计
Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
论文作者
论文摘要
近年来，不需要地面真相的自制单眼估计值吸引了人们的关注。设计轻巧但有效的模型以便将它们部署在边缘设备上是很高的兴趣。许多现有的体系结构从使用较重的骨干中受益于型号大小。本文通过轻巧的体系结构取得了可比的结果。具体而言，研究了CNN和变压器的有效组合，并提出了一种称为Lite-Mono的混合体系结构。提出了连续的扩张卷积（CDC）模块和局部全球特征相互作用（LGFI）模块。前者用于提取丰富的多尺度局部特征，后者利用自我发挥的机制将远程全局信息编码为特征。实验表明，Lite-Mono的精度较大，可训练参数少约80％。
Self-supervised monocular depth estimation that does not require ground truth for training has attracted attention in recent years. It is of high interest to design lightweight but effective models so that they can be deployed on edge devices. Many existing architectures benefit from using heavier backbones at the expense of model sizes. This paper achieves comparable results with a lightweight architecture. Specifically, the efficient combination of CNNs and Transformers is investigated, and a hybrid architecture called Lite-Mono is presented. A Consecutive Dilated Convolutions (CDC) module and a Local-Global Features Interaction (LGFI) module are proposed. The former is used to extract rich multi-scale local features, and the latter takes advantage of the self-attention mechanism to encode long-range global information into the features. Experiments demonstrate that Lite-Mono outperforms Monodepth2 by a large margin in accuracy, with about 80% fewer trainable parameters.
