We present a novel approach for unsupervised learning of depth and ego-motion from monocular video.
Models and examples built with TensorFlow
Ranked #22 on
Monocular Depth Estimation
on KITTI Eigen split
We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences.
The ability to predict depth from a single image - using recent advances in CNNs - is of increasing interest to the vision community.
In this paper we formulate structure from motion as a learning problem.
DEPTH AND CAMERA MOTION OPTICAL FLOW ESTIMATION STRUCTURE FROM MOTION
To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.
Ranked #16 on
Monocular Depth Estimation
on KITTI Eigen split
DEPTH AND CAMERA MOTION MONOCULAR DEPTH ESTIMATION VISUAL ODOMETRY
Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner.
DEPTH AND CAMERA MOTION MONOCULAR DEPTH ESTIMATION VISUAL ODOMETRY
The network first generates several basis depth maps according to the input image and optimizes the final depth as a linear combination of these basis depth maps via feature-metric BA.
We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences.
In the occluded region, as depth and camera motion can provide more reliable motion estimation, they can be used to instruct unsupervised learning of optical flow.
AUTONOMOUS DRIVING DEPTH AND CAMERA MOTION MONOCULAR DEPTH ESTIMATION MOTION ESTIMATION OPTICAL FLOW ESTIMATION