Spherical View Synthesis for Self-Supervised 360 Depth Estimation

09/17/2019
by   Nikolaos Zioulis, et al.
2

Learning based approaches for depth perception are limited by the availability of clean training data. This has led to the utilization of view synthesis as an indirect objective for learning depth estimation using efficient data acquisition procedures. Nonetheless, most research focuses on pinhole based monocular vision, with scarce works presenting results for omnidirectional input. In this work, we explore spherical view synthesis for learning monocular 360 depth in a self-supervised manner and demonstrate its feasibility. Under a purely geometrically derived formulation we present results for horizontal and vertical baselines, as well as for the trinocular case. Further, we show how to better exploit the expressiveness of traditional CNNs when applied to the equirectangular domain in an efficient manner. Finally, given the availability of ground truth depth data, our work is uniquely positioned to compare view synthesis against direct supervision in a consistent and fair manner. The results indicate that alternative research directions might be better suited to enable higher quality depth perception. Our data, models and code are publicly available at https://vcl3d.github.io/SphericalViewSynthesis/.

READ FULL TEXT

page 1

page 4

page 5

page 7

research
04/08/2019

Learning monocular depth estimation infusing traditional stereo knowledge

Depth estimation from a single image represents a fascinating, yet chall...
research
01/31/2023

Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks

Monocular Depth Estimation (MDE) is a critical component in applications...
research
08/10/2021

R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes

While self-supervised monocular depth estimation in driving scenarios ha...
research
09/13/2021

On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation

Scene depth estimation from stereo and monocular imagery is critical for...
research
08/21/2023

LightDepth: Single-View Depth Self-Supervision from Illumination Decline

Single-view depth estimation can be remarkably effective if there is eno...
research
09/03/2019

Self-Supervised Deep Depth Denoising

Depth perception is considered an invaluable source of information for v...
research
08/20/2020

DronePose: Photorealistic UAV-Assistant Dataset Synthesis for 3D Pose Estimation via a Smooth Silhouette Loss

In this work we consider UAVs as cooperative agents supporting human use...

Please sign up or login with your details

Forgot password? Click here to reset