__smbhome.uscs.susx.ac.uk_tjk30_Documents_Dorta_Structured_Uncertainty_Prediction_CVPR_2018_paper.pdf (854.49 kB)
Structured uncertainty prediction networks
conference contribution
posted on 2023-06-09, 20:23 authored by Garoe Dorta, Sara Vicente, Lourdes Agapito, Neill D F Campbell, Ivor SimpsonIvor SimpsonThis 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.
History
Publication status
- Published
File Version
- Published version
Journal
2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionISSN
1063-6919Publisher
IEEEExternal DOI
Event name
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Event location
Salt Lake City, UT, USAEvent type
conferenceEvent date
18-23 June 2018ISBN
9781538664216Department affiliated with
- Informatics Publications
Research groups affiliated with
- Data Science Research Group Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2020-01-24First Open Access (FOA) Date
2020-01-24First Compliant Deposit (FCD) Date
2020-01-24Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC