Structured Uncertainty Prediction Networks

Garoe Dorta; Sara Vicente; Lourdes Agapito; Neill Campbell; Ivor Simpson

doi:10.1109/CVPR.2018.00574

Structured Uncertainty Prediction Networks

Garoe Dorta, Sara Vicente, Lourdes Agapito, Neill Campbell, Ivor Simpson

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

40 Citations (SciVal)

152 Downloads (Pure)

Abstract

This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image.
Previous approaches have been mostly limited to predicting diagonal covariance matrices.
Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits efficient sampling and likelihood evaluation.

We demonstrate that our model can accurately reconstruct ground truth correlated residual distributions for synthetic datasets and generate plausible high frequency samples for real face images. We also illustrate the use of these predicted covariances for structure preserving image denoising.

Original language	English
Title of host publication	2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher	IEEE
Pages	5477-5485
Number of pages	9
ISBN (Electronic)	9781538664209
ISBN (Print)	9781538664216
DOIs	https://doi.org/10.1109/CVPR.2018.00574
Publication status	Published - 17 Dec 2018
Event	IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 - Duration: 18 Jun 2018 → 22 Jun 2018

Publication series

Name	IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher	IEEE
ISSN (Print)	1063-6919
ISSN (Electronic)	2575-7075

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018
Period	18/06/18 → 22/06/18

Keywords

Deep Neural Networks
Generative Models

Access to Document

10.1109/CVPR.2018.00574

cvpr18_struct_uncertainty
© 2018IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Accepted author manuscript, 922 KB

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)
Cosker, D. (PI), Bilzon, J. (CoI), Campbell, N. (CoI), Cazzola, D. (CoI), Colyer, S. (CoI), Fincham Haines, T. (CoI), Hall, P. (CoI), Kim, K. I. (CoI), Lutteroth, C. (CoI), McGuigan, P. (CoI), O'Neill, E. (CoI), Richardt, C. (CoI), Salo, A. (CoI), Seminati, E. (CoI), Tabor, A. (CoI) & Yang, Y. (CoI)
Engineering and Physical Sciences Research Council
1/09/15 → 28/02/21
Project: Research council
EPSRC Centre for Doctoral Training in Digital Entertainment
Willis, P. (PI)
1/04/14 → 30/09/22
Project: Research-related funding

Neill Campbell
- N.Campbellbath.acuk
Person: Research & Teaching, Core staff

Cite this

Structured Uncertainty Prediction Networks. / Dorta, Garoe; Vicente, Sara; Agapito, Lourdes et al.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 2018. p. 5477-5485 (IEEE/CVF Conference on Computer Vision and Pattern Recognition).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Dorta, G, Vicente, S, Agapito, L, Campbell, N & Simpson, I 2018, Structured Uncertainty Prediction Networks. in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, pp. 5477-5485, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 18/06/18. https://doi.org/10.1109/CVPR.2018.00574

@inproceedings{06498402a6994bf5b0e26349b7d21807,

title = "Structured Uncertainty Prediction Networks",

abstract = "This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image.Previous approaches have been mostly limited to predicting diagonal covariance matrices.Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits efficient sampling and likelihood evaluation.We demonstrate that our model can accurately reconstruct ground truth correlated residual distributions for synthetic datasets and generate plausible high frequency samples for real face images. We also illustrate the use of these predicted covariances for structure preserving image denoising.",

keywords = "Deep Neural Networks, Generative Models",

author = "Garoe Dorta and Sara Vicente and Lourdes Agapito and Neill Campbell and Ivor Simpson",

year = "2018",

month = dec,

day = "17",

doi = "10.1109/CVPR.2018.00574",

language = "English",

isbn = "9781538664216",

series = "IEEE/CVF Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE",

pages = "5477--5485",

booktitle = "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition",

address = "USA United States",

note = "IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 ; Conference date: 18-06-2018 Through 22-06-2018",

}

TY - GEN

T1 - Structured Uncertainty Prediction Networks

AU - Dorta, Garoe

AU - Vicente, Sara

AU - Agapito, Lourdes

AU - Campbell, Neill

AU - Simpson, Ivor

PY - 2018/12/17

Y1 - 2018/12/17

N2 - This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image.Previous approaches have been mostly limited to predicting diagonal covariance matrices.Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits efficient sampling and likelihood evaluation.We demonstrate that our model can accurately reconstruct ground truth correlated residual distributions for synthetic datasets and generate plausible high frequency samples for real face images. We also illustrate the use of these predicted covariances for structure preserving image denoising.

AB - This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image.Previous approaches have been mostly limited to predicting diagonal covariance matrices.Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits efficient sampling and likelihood evaluation.We demonstrate that our model can accurately reconstruct ground truth correlated residual distributions for synthetic datasets and generate plausible high frequency samples for real face images. We also illustrate the use of these predicted covariances for structure preserving image denoising.

KW - Deep Neural Networks

KW - Generative Models

U2 - 10.1109/CVPR.2018.00574

DO - 10.1109/CVPR.2018.00574

M3 - Chapter in a published conference proceeding

SN - 9781538664216

T3 - IEEE/CVF Conference on Computer Vision and Pattern Recognition

SP - 5477

EP - 5485

BT - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

PB - IEEE

T2 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018

Y2 - 18 June 2018 through 22 June 2018

ER -

Structured Uncertainty Prediction Networks

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)

EPSRC Centre for Doctoral Training in Digital Entertainment

Profiles

Neill Campbell

Cite this