NeuralMarker: A Framework for Learning General Marker Correspondence

09/19/2022
by   Zhaoyang Huang, et al.
0

We tackle the problem of estimating correspondences from a general marker, such as a movie poster, to an image that captures such a marker. Conventionally, this problem is addressed by fitting a homography model based on sparse feature matching. However, they are only able to handle plane-like markers and the sparse features do not sufficiently utilize appearance information. In this paper, we propose a novel framework NeuralMarker, training a neural network estimating dense marker correspondences under various challenging conditions, such as marker deformation, harsh lighting, etc. Besides, we also propose a novel marker correspondence evaluation method circumstancing annotations on real marker-image pairs and create a new benchmark. We show that NeuralMarker significantly outperforms previous methods and enables new interesting applications, including Augmented Reality (AR) and video editing.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 9

research
03/25/2021

COTR: Correspondence Transformer for Matching Across Images

We propose a novel framework for finding correspondences in images based...
research
04/07/2021

LIFE: Lighting Invariant Flow Estimation

We tackle the problem of estimating flow between two images with large l...
research
12/09/2021

GAN-Supervised Dense Visual Alignment

We propose GAN-Supervised Learning, a framework for learning discriminat...
research
05/11/2017

SCNet: Learning Semantic Correspondence

This paper addresses the problem of establishing semantic correspondence...
research
03/29/2023

CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network

Estimating the 6-DoF pose of a rigid object from a single RGB image is a...
research
11/20/2021

A Deeper Look into DeepCap

Human performance capture is a highly important computer vision problem ...
research
05/20/2019

Learning Video Representations from Correspondence Proposals

Correspondences between frames encode rich information about dynamic con...

Please sign up or login with your details

Forgot password? Click here to reset