loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Romain Guesdon ; Carlos Crispim-Junior and Laure Tougne Rodet

Affiliation: Univ. Lyon, Univ. Lyon 2, CNRS, INSA Lyon, UCBL, Centrale Lyon, LIRIS UMR5205, F-69676 Bron, France

Keyword(s): Dataset, Synthetic Generation, Neural Networks, Human Pose Transfer, Consumer Vehicle.

Abstract: The interest in driver monitoring has grown recently, especially in the context of autonomous vehicles. However, the training of deep neural networks for computer vision requires more and more images with significant diversity, which does not match the reality of the field. This lack of data prevents networks to be properly trained for certain complex tasks such as human pose transfer which aims to produce an image of a person in a target pose from another image of the same person. To tackle this problem, we propose a new synthetic dataset for pose-related tasks. By using a straightforward pipeline to increase the variety between the images, we generate 200k images with a hundred human models in different cars, environments, lighting conditions, etc. We measure the quality of the images of our dataset and compare it with other datasets from the literature. We also train a network for human pose transfer in the synthetic domain using our dataset. Results show that our dataset matches the quality of existing datasets and that it can be used to properly train a network on a complex task. We make both the images with the pose annotations and the generation scripts publicly available. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.131.13.24

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Guesdon, R.; Crispim-Junior, C. and Tougne Rodet, L. (2023). Synthetic Driver Image Generation for Human Pose-Related Tasks. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7; ISSN 2184-4321, SciTePress, pages 762-769. DOI: 10.5220/0011780800003417

@conference{visapp23,
author={Romain Guesdon. and Carlos Crispim{-}Junior. and Laure {Tougne Rodet}.},
title={Synthetic Driver Image Generation for Human Pose-Related Tasks},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={762-769},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011780800003417},
isbn={978-989-758-634-7},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Synthetic Driver Image Generation for Human Pose-Related Tasks
SN - 978-989-758-634-7
IS - 2184-4321
AU - Guesdon, R.
AU - Crispim-Junior, C.
AU - Tougne Rodet, L.
PY - 2023
SP - 762
EP - 769
DO - 10.5220/0011780800003417
PB - SciTePress