Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes

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.

Accepted to Applied Optics. Code will be made publicly available at https://github.com/zzzkkkyyy/PADENet

References in corpus (6)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Matterport3D: Learning from RGB-D Data in Indoor Environments
• Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion
• Pano3D: A Holistic Benchmark and a Solid Baseline for $360^o$ Depth Estimation