360MonoDepth: High-Resolution 360° Monocular Depth Estimation

11/30/2021
by   Manuel Rey-Area, et al.
0

360 cameras can capture complete environments in a single shot, which makes 360 imagery alluring in many computer vision tasks. However, monocular depth estimation remains a challenge for 360 data, particularly for high resolutions like 2K (2048×1024) that are important for novel-view synthesis and virtual reality applications. Current CNN-based methods do not support such high resolutions due to limited GPU memory. In this work, we propose a flexible framework for monocular depth estimation from high-resolution 360 images using tangent images. We project the 360 input image onto a set of tangent planes that produce perspective views, which are suitable for the latest, most accurate state-of-the-art perspective monocular depth estimators. We recombine the individual depth estimates using deformable multi-scale alignment followed by gradient-domain blending to improve the consistency of disparity estimates. The result is a dense, high-resolution 360 depth map with a high level of detail, also for outdoor scenes which are not supported by existing methods.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset