Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry

by   Shunkai Li, et al.

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.


page 4

page 5

page 7

page 8


Robot Localization and Mapping Final Report – Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry

Visual odometry (VO) and SLAM have been using multi-view geometry via lo...

Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

Accurate relative pose is one of the key components in visual odometry (...

ChromaGAN: An Adversarial Approach for Picture Colorization

The colorization of grayscale images is an ill-posed problem, with multi...

Self-Supervised Learning of Image Scale and Orientation

We study the problem of learning to assign a characteristic pose, i.e., ...

Self-supervised monocular depth estimation from oblique UAV videos

UAVs have become an essential photogrammetric measurement as they are af...

DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium

Self-supervised multi-frame depth estimation achieves high accuracy by c...

Please sign up or login with your details

Forgot password? Click here to reset