HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation

By Xiaoyang Lyu, Liang Liu, Mengmeng Wang, Xin Kong, Lina Liu, Yong Liu, Xinxin Chen, Yi Yuan. AAAI Conference on Artificial Intelligence, 2020

350 citations recorded by the source corpus.

Self-supervised learning shows great potential in monocular depth estimation, using image sequences as the only source of supervision. Although people try to use the high-resolution image for depth estimation, the accuracy of prediction has not been significantly improved. In this work, we find the core reason comes from the inaccurate depth estimation in large gradient regions, making the bilinear interpolation error gradually disappear as the resolution increases. To obtain more accurate depth estimation in large gradient regions, it is necessary to obtain high-resolution features with spatial and semantic information. Therefore, we present an improved DepthNet, HR-Depth, with two effective strategies: (1) re-design the skip-connection in DepthNet to get better high-resolution features and (2) propose feature fusion Squeeze-and-Excitation(fSE) module to fuse feature more efficiently. Using Resnet-18 as the encoder, HR-Depth surpasses all previous state-of-the-art(SoTA) methods with the least parameters at both high and low resolution. Moreover, previous SoTA methods are based on fairly complex and deep networks with a mass of parameters which limits their real applications. Thus we also construct a lightweight network which uses MobileNetV3 as encoder. Experiments show that the lightweight network can perform on par with many large models like Monodepth2 at high-resolution with only20%parameters. All codes and models will be available at https://github.com/shawLyu/HR-Depth.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/1c7a149cbddff67b48a6c045692fd194b404d4e8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Stefano Mattoccia
2. Fabio Tosi
3. Guan Huang
4. George Vosselman
5. Chaoqiang Zhao
6. Zheng Zhu
7. Yang Tang
8. Youming Zhang

In Media Technology

1. Stefano Mattoccia
2. Fabio Tosi
3. Chaoqiang Zhao
4. Matteo Poggi
5. Norman Kerle

Citations in the corpus

• Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation (2022, methodology): “To achieve better results a CNN-based model can use a deeper backbone or a more complicated architecture [15, 28, 44], which also results in a larger model size.”
• MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer (2022, methodology): “In our experiments, we adopt the same data augmentation detailed in [17, 30].”