SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama

25 Mar 2021  ·  Phi Vu Tran ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Room Layouts From A Single RGB Panorama PanoContext SSLayout360 3DIoU 83.30 # 2
3D Room Layouts From A Single RGB Panorama Stanford2D3D Panoramic SSLayout360 3DIoU 84.66 # 2
Corner Error 0.60 # 1
Pixel Error 1.97 # 2

Methods


No methods listed for this paper. Add relevant methods here