360^o Surface Regression with a Hyper-Sphere Loss

09/16/2019
by   Antonis Karakottas, et al.
4

Omnidirectional vision is becoming increasingly relevant as more efficient 360^o image acquisition is now possible. However, the lack of annotated 360^o datasets has hindered the application of deep learning techniques on spherical content. This is further exaggerated on tasks where ground truth acquisition is difficult, such as monocular surface estimation. While recent research approaches on the 2D domain overcome this challenge by relying on generating normals from depth cues using RGB-D sensors, this is very difficult to apply on the spherical domain. In this work, we address the unavailability of sufficient 360^o ground truth normal data, by leveraging existing 3D datasets and remodelling them via rendering. We present a dataset of 360^o images of indoor spaces with their corresponding ground truth surface normal, and train a deep convolutional neural network (CNN) on the task of monocular 360 surface estimation. We achieve this by minimizing a novel angular loss function defined on the hyper-sphere using simple quaternion algebra. We put an effort to appropriately compare with other state of the art methods trained on planar datasets and finally, present the practical applicability of our trained model on a spherical image re-lighting task using completely unseen data by qualitatively showing the promising generalization ability of our dataset and model. The dataset is available at: vcl3d.github.io/HyperSphereSurfaceRegression.

READ FULL TEXT

page 1

page 2

page 5

page 7

page 8

page 9

page 10

research
05/16/2020

Deep Lighting Environment Map Estimation from Spherical Panoramas

Estimating a scene's lighting is a very important task when compositing ...
research
10/20/2021

Depth360: Monocular Depth Estimation using Learnable Axisymmetric Camera Model for Spherical Camera Image

Self-supervised monocular depth estimation has been widely investigated ...
research
04/01/2017

Configurable, Photorealistic Image Rendering and Ground Truth Synthesis by Sampling Stochastic Grammars Representing Indoor Scenes

We propose the configurable rendering of massive quantities of photoreal...
research
07/25/2018

OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas

Recent work on depth estimation up to now has only focused on projective...
research
12/20/2019

IRS: A Large Synthetic Indoor Robotics Stereo Dataset for Disparity and Surface Normal Estimation

Indoor robotics localization, navigation and interaction heavily rely on...
research
04/10/2019

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

Many computer vision challenges require continuous outputs, but tend to ...
research
05/17/2020

Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator

Over the past decade, significant efforts have been made to improve the ...

Please sign up or login with your details

Forgot password? Click here to reset