Bayesian Helmholtz Stereopsis with Integrability Prior
- Submitting institution
-
The University of Surrey
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9006741_4
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2017.2749373
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 2265
- Volume
- 40
- Issue
- 9
- ISSN
- 0162-8828
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
-
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This research makes a step change in the modelling accuracy of scenes with complex reflectance by introducing a Bayesian reconstruction framework to enforce surface integrability. The approach was used in the EPSRC First Grant project EP/M021793/1 with industry partners (Foundry, DoubleNegative) to digitise faces and objects. It has potential for impact in other areas dealing with scenes with complex reflectance (manufacturing, health, robotics). This extends our our formulation which was awarded the Best Student Paper Prize at the International Conference on Computer Vision Theory and Applications (VISAPP2014). It led to the public release of a new benchmark dataset.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -