1DCNN+, which incorporates physics-based prior knowledge, outperforms all other networks.
Figures depict the absolute z-score values spatial distribution for Paintings 4 and 5.
-
Notifications
You must be signed in to change notification settings - Fork 0
Master Thesis: Applying Deep Learning Methods for Elemental Maps Prediction. We incorporate Physics-Based Prior Knowledge to enhance the DNNs accuracy. Specifically, we introduce PIPL (Phisics Informed Prior Layer) with constant weights - the elemental spectral signatures.
igeor/Elemental-Distribution-Mapping-with-Deep-Learning-Methods
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Master Thesis: Applying Deep Learning Methods for Elemental Maps Prediction. We incorporate Physics-Based Prior Knowledge to enhance the DNNs accuracy. Specifically, we introduce PIPL (Phisics Informed Prior Layer) with constant weights - the elemental spectral signatures.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published