SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama
arXiv:2103.13696
Abstract
Recent years have seen flourishing research on both semi-supervised learning and 3D room layout reconstruction. In this work, we explore the intersection of these two fields to advance the research objective of enabling more accurate 3D indoor scene modeling with less labeled data. We propose the first approach to learn representations of room corners and boundaries by using a combination of labeled and unlabeled data for improved layout estimation in a 360-degree panoramic scene. Through extensive comparative experiments, we demonstrate that our approach can advance layout estimation of complex indoor scenes using as few as 20 labeled examples. When coupled with a layout predictor pre-trained on synthetic data, our semi-supervised method matches the fully supervised counterpart using only 12% of the labels. Our work takes an important first step towards robust semi-supervised layout estimation that can enable many applications in 3D perception with limited labeled data.
arXiv commentCVPR 2021. File size 37MB. Project page at https://github.com/FlyreelAI/sslayout360
References in corpus (7)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Distilling the Knowledge in a Neural Network
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Joint 2D-3D-Semantic Data for Indoor Scene Understanding
- Semi-Supervised Learning with Ladder Networks
- Learning with Pseudo-Ensembles
- Distributional Smoothing with Virtual Adversarial Training