Deep meta functionals for shape representation

Gidi Littwin; Lior Wolf

doi:10.1109/ICCV.2019.00191

Deep meta functionals for shape representation

Gidi Littwin, Lior Wolf

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We present a new method for 3D shape reconstruction from a single image, in which a deep neural network directly maps an image to a vector of network weights. The network parametrized by these weights represents a 3D shape by classifying every point in the volume as either within or outside the shape. The new representation has virtually unlimited capacity and resolution, and can have an arbitrary topology. Our experiments show that it leads to more accurate shape inference from a 2D projection than the existing methods, including voxel-, silhouette-, and mesh-based methods. The code will be available at: Https: //github.com/gidilittwin/Deep-Meta.

Original language	English
Title of host publication	Proceedings - 2019 International Conference on Computer Vision, ICCV 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1824-1833
Number of pages	10
ISBN (Electronic)	9781728148038
DOIs	https://doi.org/10.1109/ICCV.2019.00191
State	Published - Oct 2019
Event	17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of Duration: 27 Oct 2019 → 2 Nov 2019

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
Volume	2019-October
ISSN (Print)	1550-5499

Conference

Conference	17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Country/Territory	Korea, Republic of
City	Seoul
Period	27/10/19 → 2/11/19

Access to Document

10.1109/ICCV.2019.00191

Cite this

Littwin, G., & Wolf, L. (2019). Deep meta functionals for shape representation. In Proceedings - 2019 International Conference on Computer Vision, ICCV 2019 (pp. 1824-1833). Article 9010022 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2019-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2019.00191

@inproceedings{b311e22e28294c04a630c0bd2520341f,

title = "Deep meta functionals for shape representation",

abstract = "We present a new method for 3D shape reconstruction from a single image, in which a deep neural network directly maps an image to a vector of network weights. The network parametrized by these weights represents a 3D shape by classifying every point in the volume as either within or outside the shape. The new representation has virtually unlimited capacity and resolution, and can have an arbitrary topology. Our experiments show that it leads to more accurate shape inference from a 2D projection than the existing methods, including voxel-, silhouette-, and mesh-based methods. The code will be available at: Https: //github.com/gidilittwin/Deep-Meta.",

author = "Gidi Littwin and Lior Wolf",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 ; Conference date: 27-10-2019 Through 02-11-2019",

year = "2019",

month = oct,

doi = "10.1109/ICCV.2019.00191",

language = "אנגלית",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1824--1833",

booktitle = "Proceedings - 2019 International Conference on Computer Vision, ICCV 2019",

address = "ארצות הברית",

}

Littwin, G & Wolf, L 2019, Deep meta functionals for shape representation. in Proceedings - 2019 International Conference on Computer Vision, ICCV 2019., 9010022, Proceedings of the IEEE International Conference on Computer Vision, vol. 2019-October, Institute of Electrical and Electronics Engineers Inc., pp. 1824-1833, 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea, Republic of, 27/10/19. https://doi.org/10.1109/ICCV.2019.00191

Deep meta functionals for shape representation. / Littwin, Gidi; Wolf, Lior.
Proceedings - 2019 International Conference on Computer Vision, ICCV 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1824-1833 9010022 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2019-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep meta functionals for shape representation

AU - Littwin, Gidi

AU - Wolf, Lior

PY - 2019/10

Y1 - 2019/10

N2 - We present a new method for 3D shape reconstruction from a single image, in which a deep neural network directly maps an image to a vector of network weights. The network parametrized by these weights represents a 3D shape by classifying every point in the volume as either within or outside the shape. The new representation has virtually unlimited capacity and resolution, and can have an arbitrary topology. Our experiments show that it leads to more accurate shape inference from a 2D projection than the existing methods, including voxel-, silhouette-, and mesh-based methods. The code will be available at: Https: //github.com/gidilittwin/Deep-Meta.

AB - We present a new method for 3D shape reconstruction from a single image, in which a deep neural network directly maps an image to a vector of network weights. The network parametrized by these weights represents a 3D shape by classifying every point in the volume as either within or outside the shape. The new representation has virtually unlimited capacity and resolution, and can have an arbitrary topology. Our experiments show that it leads to more accurate shape inference from a 2D projection than the existing methods, including voxel-, silhouette-, and mesh-based methods. The code will be available at: Https: //github.com/gidilittwin/Deep-Meta.

UR - http://www.scopus.com/inward/record.url?scp=85081898249&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2019.00191

DO - 10.1109/ICCV.2019.00191

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85081898249

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1824

EP - 1833

BT - Proceedings - 2019 International Conference on Computer Vision, ICCV 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019

Y2 - 27 October 2019 through 2 November 2019

ER -

Deep meta functionals for shape representation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this