SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama
This addresses the challenge of accurate 3D scene modeling for applications in 3D perception when labeled data is scarce, representing an incremental advancement at the intersection of semi-supervised learning and layout estimation.
The paper tackles the problem of 3D indoor layout estimation from 360-degree panoramas with limited labeled data, proposing a semi-supervised approach that matches fully supervised performance using only 12% of labels and works with as few as 20 labeled examples.
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.