Generative Landmarks

Ferman, David; Bharaj, Gaurav

Generative Landmarks

Files

009-010.pdf (839.02 KB)

poster1009_009-010.pdf (2.51 MB)

Date

2021

Authors

Ferman, David
Bharaj, Gaurav

Publisher

The Eurographics Association

Abstract

We propose a general purpose approach to detect landmarks with improved temporal consistency, and personalization. Most sparse landmark detection methods rely on laborious, manually labelled landmarks, where inconsistency in annotations over a temporal volume leads to sub-optimal landmark learning. Further, high-quality landmarks with personalization is often hard to achieve. We pose landmark detection as an image translation problem. We capture two sets of unpaired marked (with paint) and unmarked videos. We then use a generative adversarial network and cyclic consistency to predict deformations of landmark templates that simulate markers on unmarked images until these images are indistinguishable from ground-truth marked images. Our novel method does not rely on manually labelled priors, is temporally consistent, and image class agnostic - face, and hand landmarks detection examples are shown.

        @inproceedings{10.2312:egp.20211029
,
booktitle = {Eurographics 2021 - Posters
},
editor = {Bittner, Jirí and Waldner, Manuela
},
title = {{Generative Landmarks
}},
author = {Ferman, David and 
Bharaj, Gaurav
},
year = {2021
},
publisher = {The Eurographics Association
},
ISSN = {1017-4656
},
ISBN = {978-3-03868-134-2
},
DOI = {10.2312/egp.20211029
}
}