Learning a hierarchical latent-variable model of 3D shapes

Shikun Liu, C. Lee Giles, Alexander Ororbia

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion. Through the use of skip-connections, our model can successfully learn and infer a latent, hierarchical representation of objects. Furthermore, realistic 3D objects can be easily generated by sampling the VSL's latent probabilistic manifold. We show that our generative model can be trained end-to-end from 2D images to perform single image 3D model retrieval. Experiments show, both quantitatively and qualitatively, the improved generalization of our proposed model over a range of tasks, performing better or comparable to various state-of-the-art alternatives.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 International Conference on 3D Vision, 3DV 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages542-551
Number of pages10
ISBN (Electronic)9781538684252
DOIs
StatePublished - Oct 12 2018
Event6th International Conference on 3D Vision, 3DV 2018 - Verona, Italy
Duration: Sep 5 2018Sep 8 2018

Publication series

NameProceedings - 2018 International Conference on 3D Vision, 3DV 2018

Other

Other6th International Conference on 3D Vision, 3DV 2018
CountryItaly
CityVerona
Period9/5/189/8/18

Fingerprint

Sampling
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Liu, S., Giles, C. L., & Ororbia, A. (2018). Learning a hierarchical latent-variable model of 3D shapes. In Proceedings - 2018 International Conference on 3D Vision, 3DV 2018 (pp. 542-551). [8491006] (Proceedings - 2018 International Conference on 3D Vision, 3DV 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/3DV.2018.00068
Liu, Shikun ; Giles, C. Lee ; Ororbia, Alexander. / Learning a hierarchical latent-variable model of 3D shapes. Proceedings - 2018 International Conference on 3D Vision, 3DV 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 542-551 (Proceedings - 2018 International Conference on 3D Vision, 3DV 2018).
@inproceedings{8be379c3dff1490fb9ce3789e9901b37,
title = "Learning a hierarchical latent-variable model of 3D shapes",
abstract = "We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion. Through the use of skip-connections, our model can successfully learn and infer a latent, hierarchical representation of objects. Furthermore, realistic 3D objects can be easily generated by sampling the VSL's latent probabilistic manifold. We show that our generative model can be trained end-to-end from 2D images to perform single image 3D model retrieval. Experiments show, both quantitatively and qualitatively, the improved generalization of our proposed model over a range of tasks, performing better or comparable to various state-of-the-art alternatives.",
author = "Shikun Liu and Giles, {C. Lee} and Alexander Ororbia",
year = "2018",
month = "10",
day = "12",
doi = "10.1109/3DV.2018.00068",
language = "English (US)",
series = "Proceedings - 2018 International Conference on 3D Vision, 3DV 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "542--551",
booktitle = "Proceedings - 2018 International Conference on 3D Vision, 3DV 2018",
address = "United States",

}

Liu, S, Giles, CL & Ororbia, A 2018, Learning a hierarchical latent-variable model of 3D shapes. in Proceedings - 2018 International Conference on 3D Vision, 3DV 2018., 8491006, Proceedings - 2018 International Conference on 3D Vision, 3DV 2018, Institute of Electrical and Electronics Engineers Inc., pp. 542-551, 6th International Conference on 3D Vision, 3DV 2018, Verona, Italy, 9/5/18. https://doi.org/10.1109/3DV.2018.00068

Learning a hierarchical latent-variable model of 3D shapes. / Liu, Shikun; Giles, C. Lee; Ororbia, Alexander.

Proceedings - 2018 International Conference on 3D Vision, 3DV 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 542-551 8491006 (Proceedings - 2018 International Conference on 3D Vision, 3DV 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Learning a hierarchical latent-variable model of 3D shapes

AU - Liu, Shikun

AU - Giles, C. Lee

AU - Ororbia, Alexander

PY - 2018/10/12

Y1 - 2018/10/12

N2 - We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion. Through the use of skip-connections, our model can successfully learn and infer a latent, hierarchical representation of objects. Furthermore, realistic 3D objects can be easily generated by sampling the VSL's latent probabilistic manifold. We show that our generative model can be trained end-to-end from 2D images to perform single image 3D model retrieval. Experiments show, both quantitatively and qualitatively, the improved generalization of our proposed model over a range of tasks, performing better or comparable to various state-of-the-art alternatives.

AB - We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion. Through the use of skip-connections, our model can successfully learn and infer a latent, hierarchical representation of objects. Furthermore, realistic 3D objects can be easily generated by sampling the VSL's latent probabilistic manifold. We show that our generative model can be trained end-to-end from 2D images to perform single image 3D model retrieval. Experiments show, both quantitatively and qualitatively, the improved generalization of our proposed model over a range of tasks, performing better or comparable to various state-of-the-art alternatives.

UR - http://www.scopus.com/inward/record.url?scp=85056748850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056748850&partnerID=8YFLogxK

U2 - 10.1109/3DV.2018.00068

DO - 10.1109/3DV.2018.00068

M3 - Conference contribution

AN - SCOPUS:85056748850

T3 - Proceedings - 2018 International Conference on 3D Vision, 3DV 2018

SP - 542

EP - 551

BT - Proceedings - 2018 International Conference on 3D Vision, 3DV 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Liu S, Giles CL, Ororbia A. Learning a hierarchical latent-variable model of 3D shapes. In Proceedings - 2018 International Conference on 3D Vision, 3DV 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 542-551. 8491006. (Proceedings - 2018 International Conference on 3D Vision, 3DV 2018). https://doi.org/10.1109/3DV.2018.00068