English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches

MPS-Authors
/persons/resource/persons79468

Sattar,  Hosnieh
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons118756

Pons-Moll,  Gerard
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1905.11503.pdf
(Preprint), 7MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Sattar, H., Krombholz, K., Pons-Moll, G., & Fritz, M. (2019). Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches. Retrieved from http://arxiv.org/abs/1905.11503.


Cite as: http://hdl.handle.net/21.11116/0000-0003-B2E5-1
Abstract
Modern approaches to pose and body shape estimation have recently achieved strong performance even under challenging real-world conditions. Even from a single image of a clothed person, a realistic looking body shape can be inferred that captures a users' weight group and body shape type well. This opens up a whole spectrum of applications -- in particular in fashion -- where virtual try-on and recommendation systems can make use of these new and automatized cues. However, a realistic depiction of the undressed body is regarded highly private and therefore might not be consented by most people. Hence, we ask if the automatic extraction of such information can be effectively evaded. While adversarial perturbations have been shown to be effective for manipulating the output of machine learning models -- in particular, end-to-end deep learning approaches -- state of the art shape estimation methods are composed of multiple stages. We perform the first investigation of different strategies that can be used to effectively manipulate the automatic shape estimation while preserving the overall appearance of the original image.