---
_id: '8186'
abstract:
- lang: eng
text: "Numerous methods have been proposed for probabilistic generative modelling
of\r\n3D objects. However, none of these is able to produce textured objects,
which\r\nrenders them of limited use for practical tasks. In this work, we present
the\r\nfirst generative model of textured 3D meshes. Training such a model would\r\ntraditionally
require a large dataset of textured meshes, but unfortunately,\r\nexisting datasets
of meshes lack detailed textures. We instead propose a new\r\ntraining methodology
that allows learning from collections of 2D images without\r\nany 3D information.
To do so, we train our model to explain a distribution of\r\nimages by modelling
each image as a 3D foreground object placed in front of a\r\n2D background. Thus,
it learns to generate meshes that when rendered, produce\r\nimages similar to
those in its training set.\r\n A well-known problem when generating meshes with
deep networks is the\r\nemergence of self-intersections, which are problematic
for many use-cases. As a\r\nsecond contribution we therefore introduce a new generation
process for 3D\r\nmeshes that guarantees no self-intersections arise, based on
the physical\r\nintuition that faces should push one another out of the way as
they move.\r\n We conduct extensive experiments on our approach, reporting quantitative
and\r\nqualitative results on both synthetic data and natural images. These show
our\r\nmethod successfully learns to generate plausible and diverse textured 3D\r\nsamples
for five challenging object classes."
article_processing_charge: No
author:
- first_name: Paul M
full_name: Henderson, Paul M
id: 13C09E74-18D9-11E9-8878-32CFE5697425
last_name: Henderson
orcid: 0000-0002-5198-7445
- first_name: Vagia
full_name: Tsiminaki, Vagia
last_name: Tsiminaki
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Henderson PM, Tsiminaki V, Lampert C. Leveraging 2D data to learn textured
3D mesh generation. In: Proceedings of the IEEE/CVF Conference on Computer
Vision and Pattern Recognition. IEEE; 2020:7498-7507. doi:10.1109/CVPR42600.2020.00752'
apa: 'Henderson, P. M., Tsiminaki, V., & Lampert, C. (2020). Leveraging 2D data
to learn textured 3D mesh generation. In Proceedings of the IEEE/CVF Conference
on Computer Vision and Pattern Recognition (pp. 7498–7507). Virtual: IEEE.
https://doi.org/10.1109/CVPR42600.2020.00752'
chicago: Henderson, Paul M, Vagia Tsiminaki, and Christoph Lampert. “Leveraging
2D Data to Learn Textured 3D Mesh Generation.” In Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, 7498–7507. IEEE, 2020.
https://doi.org/10.1109/CVPR42600.2020.00752.
ieee: P. M. Henderson, V. Tsiminaki, and C. Lampert, “Leveraging 2D data to learn
textured 3D mesh generation,” in Proceedings of the IEEE/CVF Conference on
Computer Vision and Pattern Recognition, Virtual, 2020, pp. 7498–7507.
ista: 'Henderson PM, Tsiminaki V, Lampert C. 2020. Leveraging 2D data to learn textured
3D mesh generation. Proceedings of the IEEE/CVF Conference on Computer Vision
and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition,
7498–7507.'
mla: Henderson, Paul M., et al. “Leveraging 2D Data to Learn Textured 3D Mesh Generation.”
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,
IEEE, 2020, pp. 7498–507, doi:10.1109/CVPR42600.2020.00752.
short: P.M. Henderson, V. Tsiminaki, C. Lampert, in:, Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, IEEE, 2020, pp. 7498–7507.
conference:
end_date: 2020-06-19
location: Virtual
name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
start_date: 2020-06-14
date_created: 2020-07-31T16:53:49Z
date_published: 2020-07-01T00:00:00Z
date_updated: 2023-10-17T07:37:11Z
day: '01'
ddc:
- '004'
department:
- _id: ChLa
doi: 10.1109/CVPR42600.2020.00752
external_id:
arxiv:
- '2004.04180'
file:
- access_level: open_access
content_type: application/pdf
creator: phenders
date_created: 2020-07-31T16:57:12Z
date_updated: 2020-07-31T16:57:12Z
file_id: '8187'
file_name: paper.pdf
file_size: 10262773
relation: main_file
success: 1
file_date_updated: 2020-07-31T16:57:12Z
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://openaccess.thecvf.com/content_CVPR_2020/papers/Henderson_Leveraging_2D_Data_to_Learn_Textured_3D_Mesh_Generation_CVPR_2020_paper.pdf
month: '07'
oa: 1
oa_version: Submitted Version
page: 7498-7507
publication: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern
Recognition
publication_identifier:
eisbn:
- '9781728171685'
eissn:
- 2575-7075
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Leveraging 2D data to learn textured 3D mesh generation
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2020'
...