Self-supervised monocular depth estimation has always attracted attention because it does not require ground truth data. Designing a lightweight architecture capable of fast inference is crucial for deployment on mobile devices. The current network effectively integrates Convolutional Neural Networks (CNN) with Transformers, achieving significant improvements in accuracy. However, this advantage comes at the cost of an increase in model size and a significant reduction in inference speed. In this study, we propose a network named Repmono, which includes LCKT module with a large convolutional kernel and RepTM module based on the structural reparameterisation technique. With the combination of these two modules, our network achieves both local and global feature extraction with a smaller number of parameters and significantly enhances inference speed. Our network, with 2.31MB parameters, shows significant accuracy improvements over Monodepth2 in experiments on the KITTI dataset. With uniform input dimensions, our network’s inference speed is 53.7% faster than R-MSFM6, 60.1% faster than Monodepth2, and 81.1% faster than MonoVIT-small. Our code is available at https://github.com/txc320382/Repmono.

自监督单目深度估计一直备受关注，因为它不需要地面真实数据。设计能够快速推理的轻量级架构对于移动设备上的部署至关重要。当前的网络有效地将卷积神经网络（CNN）与 Transformer 结合起来，实现了准确性的显着提高。然而，这种优势是以模型大小增加和推理速度显着降低为代价的。在本研究中，我们提出了一个名为 Repmono 的网络，其中包括具有大卷积核的 LCKT 模块和基于结构重参数化技术的 RepTM 模块。通过这两个模块的结合，我们的网络以更少的参数实现了局部和全局特征提取，并显着提高了推理速度。我们的网络具有 2.31MB 参数，在 KITTI 数据集上的实验中显示出比 Monodepth2 显着提高的准确性。在统一的输入维度下，我们的网络的推理速度比 R-MSFM6 快 53.7%，比 Monodepth2 快 60.1%，比 MonoVIT-small 快 81.1%。我们的代码可在 https://github.com/txc320382/Repmono 获取。