Implementation Details: topo_feat_s

marrlab / SHAPR_torch

SHAPR: Code for "Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction"

https://shapr.topology.rocks

BSD 3-Clause "New" or "Revised" License

37 stars 10 forks source link

Implementation Details: topo_feat_s #6

Closed VincentYCYao closed 2 months ago

VincentYCYao commented 2 months ago

Hi,

In the _settings.py file, we have the default setting "topo_feat_s=False", which means "do no use superlevel features". But in the paper, the authors applied a superlevel set filtration, which means constructing cubical complexes by retaining vertices above a sequence of thresholds.

Could you answer the questions below? 1) which setting for "topo_feat_s" is used 2) from your experience, what is the effect of superlevel and sublevel set filtration?

Best, Vincent

Pseudomanifold commented 2 months ago

We typically ran sweeps in which we made the choice configurable (see shapr/sweeps/topology-all-dims.yaml). In practice, the choice does not make a substantial difference, given the duality theorems. Hope that helps! Feel free to reopen.