360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Zhijie, Lin, Chunyu, Zhang, Junsong, Nie, Lang, Liao, Kang, Zhao, Yao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914928160407552
author Shen, Zhijie
Lin, Chunyu
Zhang, Junsong
Nie, Lang
Liao, Kang
Zhao, Yao
author_facet Shen, Zhijie
Lin, Chunyu
Zhang, Junsong
Nie, Lang
Liao, Kang
Zhao, Yao
contents Existing panoramic layout estimation solutions tend to recover room boundaries from a vertically compressed sequence, yielding imprecise results as the compression process often muddles the semantics between various planes. Besides, these data-driven approaches impose an urgent demand for massive data annotations, which are laborious and time-consuming. For the first problem, we propose an orthogonal plane disentanglement network (termed DOPNet) to distinguish ambiguous semantics. DOPNet consists of three modules that are integrated to deliver distortion-free, semantics-clean, and detail-sharp disentangled representations, which benefit the subsequent layout recovery. For the second problem, we present an unsupervised adaptation technique tailored for horizon-depth and ratio representations. Concretely, we introduce an optimization strategy for decision-level layout analysis and a 1D cost volume construction method for feature-level multi-view aggregation, both of which are designed to fully exploit the geometric consistency across multiple perspectives. The optimizer provides a reliable set of pseudo-labels for network training, while the 1D cost volume enriches each view with comprehensive scene information derived from other perspectives. Extensive experiments demonstrate that our solution outperforms other SoTA models on both monocular layout estimation and multi-view layout estimation tasks. Cobe can be available at https://github.com/zhijieshen-bjtu/MV-DOPNet.
format Preprint
id arxiv_https___arxiv_org_abs_2312_16268
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle 360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception
Shen, Zhijie
Lin, Chunyu
Zhang, Junsong
Nie, Lang
Liao, Kang
Zhao, Yao
Computer Vision and Pattern Recognition
Existing panoramic layout estimation solutions tend to recover room boundaries from a vertically compressed sequence, yielding imprecise results as the compression process often muddles the semantics between various planes. Besides, these data-driven approaches impose an urgent demand for massive data annotations, which are laborious and time-consuming. For the first problem, we propose an orthogonal plane disentanglement network (termed DOPNet) to distinguish ambiguous semantics. DOPNet consists of three modules that are integrated to deliver distortion-free, semantics-clean, and detail-sharp disentangled representations, which benefit the subsequent layout recovery. For the second problem, we present an unsupervised adaptation technique tailored for horizon-depth and ratio representations. Concretely, we introduce an optimization strategy for decision-level layout analysis and a 1D cost volume construction method for feature-level multi-view aggregation, both of which are designed to fully exploit the geometric consistency across multiple perspectives. The optimizer provides a reliable set of pseudo-labels for network training, while the 1D cost volume enriches each view with comprehensive scene information derived from other perspectives. Extensive experiments demonstrate that our solution outperforms other SoTA models on both monocular layout estimation and multi-view layout estimation tasks. Cobe can be available at https://github.com/zhijieshen-bjtu/MV-DOPNet.
title 360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.16268