CTRL-C: Camera calibration TRansformer with Line-Classification

09/06/2021
by   Jinwoo Lee, et al.
6

Single image camera calibration is the task of estimating the camera parameters from a single input image, such as the vanishing points, focal length, and horizon line. In this work, we propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration, which directly estimates the camera parameters from an image and a set of line segments. Our network adopts the transformer architecture to capture the global structure of an image with multi-modal inputs in an end-to-end manner. We also propose an auxiliary task of line classification to train the network to extract the global geometric information from lines effectively. Our experiments demonstrate that CTRL-C outperforms the previous state-of-the-art methods on the Google Street View and SUN360 benchmark datasets.

READ FULL TEXT

page 1

page 3

page 6

page 8

page 12

page 13

page 14

research
07/23/2020

Neural Geometric Parser for Single Image Camera Calibration

We propose a neural geometric parser learning single image camera calibr...
research
08/25/2022

A Deep Perceptual Measure for Lens and Camera Calibration

Image editing and compositing have become ubiquitous in entertainment, f...
research
08/15/2022

HoW-3D: Holistic 3D Wireframe Perception from a Single Image

This paper studies the problem of holistic 3D wireframe perception (HoW-...
research
05/09/2023

FishRecGAN: An End to End GAN Based Network for Fisheye Rectification and Calibration

We propose an end-to-end deep learning approach to rectify fisheye image...
research
04/07/2016

Horizon Lines in the Wild

The horizon line is an important contextual attribute for a wide variety...
research
01/08/2023

Equivalence of Two Expressions of Principal Line

Geometry-based camera calibration using principal line is more precise a...
research
08/05/2017

SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis

This paper proposes an end-to-end learning framework for multiview stere...

Please sign up or login with your details

Forgot password? Click here to reset