Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes

TL;DR

This paper presents a novel approach for panoramic depth estimation in indoor scenes, combining supervised and unsupervised learning, traditional stereo methods, and network improvements to enhance accuracy and field of view.

Contribution

It extends PADENet for indoor panoramic depth estimation, improves training for panoramic images, and fuses stereo matching with deep learning for better accuracy.

Findings

Effective depth estimation in indoor panoramic scenes

Improved accuracy through stereo and deep learning fusion

Enhanced training process for panoramic image characteristics

Abstract

Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree geometric sensing, traditional stereo matching algorithms for depth estimation are limited due to large noise, low accuracy, and strict requirements for multi-camera calibration. In this work, for a unified surrounding perception, we introduce panoramic images to obtain larger field of view. We extend PADENet first appeared in our previous conference work for outdoor scene understanding, to perform panoramic monocular depth estimation with a focus for indoor scenes. At the same time, we improve the training process of the neural network adapted to the characteristics of panoramic images. In addition, we fuse traditional stereo matching algorithm with deep learning methods and further improve the accuracy of depth predictions. With a comprehensive variety of experiments, this research demonstrates the effectiveness of our schemes aiming for indoor scene perception.