DeepAI
Log In Sign Up

Learning to Parse Wireframes in Images of Man-Made Environments

07/15/2020
by   Kun Huang, et al.
15

In this paper, we propose a learning-based approach to the task of automatically extracting a "wireframe" representation for images of cluttered man-made environments. The wireframe (see Fig. 1) contains all salient straight lines and their junctions of the scene that encode efficiently and accurately large-scale geometry and object shapes. To this end, we have built a very large new dataset of over 5,000 images with wireframes thoroughly labelled by humans. We have proposed two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support, respectively. The networks trained on our dataset have achieved significantly better performance than state-of-the-art methods for junction detection and line segment detection, respectively. We have conducted extensive experiments to evaluate quantitatively and qualitatively the wireframes obtained by our method, and have convincingly shown that effectively and efficiently parsing wireframes for images of man-made environments is a feasible goal within reach. Such wireframes could benefit many important visual tasks such as feature correspondence, 3D reconstruction, vision-based mapping, localization, and navigation. The data and source code are available at https://github.com/huangkuns/wireframe.

READ FULL TEXT

page 1

page 3

page 4

page 8

page 13

page 14

page 15

05/08/2019

End-to-End Wireframe Parsing

We present a conceptually simple yet effective algorithm to detect wiref...
11/06/2020

ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras

Line segment detection is essential for high-level tasks in computer vis...
03/31/2020

Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence

We present a novel learning-based approach for computing correspondences...
10/20/2020

TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power Lines

Accurate detection and segmentation of transmission towers (TTs) and pow...
08/23/2018

Learning Human-Object Interactions by Graph Parsing Neural Networks

This paper addresses the task of detecting and recognizing human-object ...
03/31/2020

SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings

Spatial reasoning is an important component of human intelligence. We ca...
05/17/2019

Learning to Reconstruct 3D Manhattan Wireframes from a Single Image

In this paper, we propose a method to obtain a compact and accurate 3D w...