Jadie Adams

Results 9 issues of Jadie Adams

Hello, thanks for providing your code. I have a question, [LPBNN_layers line 75](https://github.com/giannifranchi/LP_BNN/blob/70f02c99539726256c577104494ac6dd43ced583/networks/LPBNN_layers.py#L75C1-L75C99) is: `embedded_mean, embedded_logvar=self.encoder_fcmean(embedded),self.encoder_fcmean(embedded)` Should this not be: `embedded_mean, embedded_logvar=self.encoder_fcmean(embedded),self.encoder_fcvar(embedded)` As it is, it appears to be enforcing...

Currently, the generalization is measured using the distance between true and reconstructed unseen particles, and specificity is measured using the distance between sampled particles and closest real particles. The problem...

Enhancement
Tools: Analyze

One qualitiative metric we use to analyze correspondence is the consistency of particle neighborhoods across shapes. This can be quantitatively captured as the mapping error as described in [Point2SSM](https://arxiv.org/pdf/2305.14486.pdf) (Equation...

Feature Request
Tools: Analyze

Create datasets that can be used for consistent DeepSSM benchmarking. Training data must include: - Original and groomed images - Original and groomed shapes (meshes or binary segmentations) - Cutting...

DeepSSM

We want to add functionality we have for Procrustes as a Python tool. This way given a local particle system, we can compute the world particles and transforms.

Priority: High
Tools: Consolidation
Python API

Add an optional step to data augmentation that uses histogram matching to create augmented images with different intensity profiles.

Priority: Low
Feature Request

When I optimize with geodesics with some meshes I get an error like: `ERROR: Error: checkFinite() failure: Non-finite matrix entry [6111,6111] = nan` This is happening before optimization iterations, I...

Bug

When use cases are changed, they should be automatically run and the output xmls and shape models should be automatically uploaded to the portal.

Priority: High
QA/Testing

Currently, if you want to compute the distance between two meshes and save it as a scalar field (so you can visualize it as a heat map), using the Python...

Enhancement
Python API