Unsupervised Learning of Depth and Ego-Motion from Cylindrical Panoramic Video with Applications for Virtual Reality
This addresses depth estimation for applications like virtual reality and robotics, but is incremental as it adapts existing methods to a new projection format.
The paper tackles unsupervised learning of depth and ego-motion from cylindrical panoramic video, showing that this approach produces high-quality depth maps and improves ego-motion accuracy with an increased field-of-view, as evaluated on synthetic and real datasets.
We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D modeling, and autonomous robotic navigation. In contrast to previous approaches for applying convolutional neural networks to panoramic imagery, we use the cylindrical panoramic projection which allows for the use of the traditional CNN layers such as convolutional filters and max pooling without modification. Our evaluation of synthetic and real data shows that unsupervised learning of depth and ego-motion on cylindrical panoramic images can produce high-quality depth maps and that an increased field-of-view improves ego-motion estimation accuracy. We create two new datasets to evaluate our approach: a synthetic dataset created using the CARLA simulator, and Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting. We also apply our network to the problem of converting monocular panoramas to stereo panoramas.