3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform

07/19/2022
by   Yining Zhao, et al.
0

Significant geometric structures can be compactly described by global wireframes in the estimation of 3D room layout from a single panoramic image. Based on this observation, we present an alternative approach to estimate the walls in 3D space by modeling long-range geometric patterns in a learnable Hough Transform block. We transform the image feature from a cubemap tile to the Hough space of a Manhattan world and directly map the feature to the geometric output. The convolutional layers not only learn the local gradient-like line features, but also utilize the global information to successfully predict occluded walls with a simple network structure. Unlike most previous work, the predictions are performed individually on each cubemap tile, and then assembled to get the layout estimation. Experimental results show that we achieve comparable results with recent state-of-the-art in prediction accuracy and performance. Code is available at https://github.com/Starrah/DMH-Net.

READ FULL TEXT

page 11

page 13

page 22

page 24

page 25

page 26

page 27

page 28

research
04/19/2021

OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas

Given a single RGB panorama, the goal of 3D layout reconstruction is to ...
research
11/29/2018

DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama

We present a deep learning framework, called DuLa-Net, to predict Manhat...
research
03/30/2022

Self-supervised 360^∘ Room Layout Estimation

We present the first self-supervised method to train panoramic room layo...
research
03/02/2023

Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness

Based on the Manhattan World assumption, most existing indoor layout est...
research
03/31/2021

Layout-Guided Novel View Synthesis from a Single Indoor Panorama

Existing view synthesis methods mainly focus on the perspective images a...
research
07/18/2020

Deep Hough-Transform Line Priors

Classical work on line segment detection is knowledge-based; it uses car...
research
02/07/2021

Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas

It has been shown that global scene understanding tasks like layout esti...

Please sign up or login with your details

Forgot password? Click here to reset