# SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1906.08889 · HTML: https://mlsanity.com/paper/1906.08889/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2019.

## Built on by (most cited first, 5 of 5)

- [3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video](https://mlsanity.com/paper/2112.03045/) (2021)
- [Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition](https://mlsanity.com/paper/2212.01538/) (2022)
- [Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos](https://mlsanity.com/paper/2106.03505/) (2021)
- [Self-supervised Multi-task Learning Framework for Safety and Health-Oriented Connected Driving Environment Perception using Onboard Camera](https://mlsanity.com/paper/2306.11822/) (2023)
- [Enhanced Encoder-Decoder Architecture for Accurate Monocular Depth Estimation](https://mlsanity.com/paper/2410.11610/) (2024)

## Abstract (arXiv)

Recently end-to-end unsupervised deep learning methods have achieved an effect beyond geometric methods for visual depth and ego-motion estimation tasks. These data-based learning methods perform more robustly and accurately in some of the challenging scenes. The encoder-decoder network has been widely used in the depth estimation and the RCNN has brought significant improvements in the ego-motion estimation. Furthermore, the latest use of Generative Adversarial Nets(GANs) in depth and ego-motion estimation has demonstrated that the estimation could be further improved by generating pictures in the game learning process. This paper proposes a novel unsupervised network system for visual depth and ego-motion estimation: Stacked Generative Adversarial Network(SGANVO). It consists of a stack of GAN layers, of which the lowest layer estimates the depth and ego-motion while the higher layers estimate the spatial features. It can also capture the temporal dynamic due to the use of a recurrent representation across the layers. See Fig.1 for details. We select the most commonly used KITTI [1] data set for evaluation. The evaluation results show that our proposed method can produce better or comparable results in depth and ego-motion estimation.