# Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry

arXiv: https://arxiv.org/abs/1908.08704 · HTML: https://mlsanity.com/paper/1908.08704/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2019.

## Built on by (most cited first, 18 of 18)

- [RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes](https://mlsanity.com/paper/2303.04456/) (2023)
- [Generalizing to the Open World: Deep Visual Odometry with Online Adaptation](https://mlsanity.com/paper/2103.15279/) (2021)
- [XVO: Generalized Visual Odometry via Cross-Modal Self-Training](https://mlsanity.com/paper/2309.16772/) (2023)
- [VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals](https://mlsanity.com/paper/2104.06789/) (2021)
- [Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network](https://mlsanity.com/paper/2308.05605/) (2023)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [Self-supervised Visual-LiDAR Odometry with Flip Consistency](https://mlsanity.com/paper/2101.01322/) (2021)
- [Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling](https://mlsanity.com/paper/2202.13353/) (2022)
- [Globally Consistent Video Depth and Pose Estimation with Efficient Test-Time Training](https://mlsanity.com/paper/2208.02709/) (2022)
- [Pseudo-LiDAR for Visual Odometry](https://mlsanity.com/paper/2209.01567/) (2022)
- [A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation](https://mlsanity.com/paper/2203.04812/) (2022)
- [Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2211.11066/) (2022)
- [A survey on deep learning approaches for data integration in autonomous driving system](https://mlsanity.com/paper/2306.11740/) (2023)
- [Unsupervised Monocular Depth Estimation Based on Hierarchical Feature-Guided Diffusion](https://mlsanity.com/paper/2406.09782/) (2024)
- [An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World](https://mlsanity.com/paper/2504.11698/) (2025)
- [Robot Localization and Mapping Final Report -- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry](https://mlsanity.com/paper/2309.04147/) (2023)
- [PRAM: Place Recognition Anywhere Model for Efficient Visual Localization](https://mlsanity.com/paper/2404.07785/) (2024)
- [ORB-SfMLearner: ORB-Guided Self-supervised Visual Odometry with Selective Online Adaptation](https://mlsanity.com/paper/2409.11692/) (2024)

## Abstract (arXiv)

We propose a self-supervised learning framework for visual odometry (VO) that incorporates correlation of consecutive frames and takes advantage of adversarial learning. Previous methods tackle self-supervised VO as a local structure from motion (SfM) problem that recovers depth from single image and relative poses from image pairs by minimizing photometric loss between warped and captured images. As single-view depth estimation is an ill-posed problem, and photometric loss is incapable of discriminating distortion artifacts of warped images, the estimated depth is vague and pose is inaccurate. In contrast to previous methods, our framework learns a compact representation of frame-to-frame correlation, which is updated by incorporating sequential information. The updated representation is used for depth estimation. Besides, we tackle VO as a self-supervised image generation task and take advantage of Generative Adversarial Networks (GAN). The generator learns to estimate depth and pose to generate a warped target image. The discriminator evaluates the quality of generated image with high-level structural perception that overcomes the problem of pixel-wise loss in previous methods. Experiments on KITTI and Cityscapes datasets show that our method obtains more accurate depth with details preserved and predicted pose outperforms state-of-the-art self-supervised methods significantly.