Distortion-Aware Self-Supervised 360° Depth Estimation from A Single Equirectangular Projection Image
This addresses the problem of limited supervision and distortion in 360° depth estimation for applications in VR/AR or robotics, though it is incremental as it builds on existing self-supervised approaches.
The paper tackles depth estimation from a single 360° image in open environments by proposing a distortion-aware self-supervised method that directly uses equirectangular projection, outperforming state-of-the-art techniques in outdoor scenes.
360° images are widely available over the last few years. This paper proposes a new technique for single 360° image depth prediction under open environments. Depth prediction from a 360° single image is not easy for two reasons. One is the limitation of supervision datasets - the currently available dataset is limited to indoor scenes. The other is the problems caused by Equirectangular Projection Format (ERP), commonly used for 360° images, that are coordinate and distortion. There is only one method existing that uses cube map projection to produce six perspective images and apply self-supervised learning using motion pictures for perspective depth prediction to deal with these problems. Different from the existing method, we directly use the ERP format. We propose a framework of direct use of ERP with coordinate conversion of correspondences and distortion-aware upsampling module to deal with the ERP related problems and extend a self-supervised learning method for open environments. For the experiments, we firstly built a dataset for the evaluation, and quantitatively evaluate the depth prediction in outdoor scenes. We show that it outperforms the state-of-the-art technique