OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas

Abstract

Recent work on depth estimation up to now has only focused on projective images ignoring 360 content which is now increasingly and more easily produced. We show that monocular depth estimation models trained on traditional images produce sub-optimal results on omnidirectional images, showcasing the need for training directly on 360 datasets, which however, are hard to acquire. In this work, we circumvent the challenges associated with acquiring high quality 360 datasets with ground truth depth annotations, by re-using recently released large scale 3D datasets and re-purposing them to 360 via rendering. This dataset, which is considerably larger than similar projective datasets, is publicly offered to the community to enable future research in this direction. We use this dataset to learn in an end-to-end fashion the task of depth estimation from 360 images. We show promising results in our synthesized data as well as in unseen realistic images.

Pre-print to appear in ECCV18

Cited by in corpus (6)

• Pano3D: A Holistic Benchmark and a Solid Baseline for $360^o$ Depth Estimation
• BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
• Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning
• Convolutions on Spherical Images
• $S^2$Net: Accurate Panorama Depth Estimation on Spherical Surface
• Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues