Get 3D object and scene using new regularization term and quadratic layers with StEik
Get 3D object and scene using new regularization term and quadratic layers with StEik
StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation
arXiv paper abstract https://arxiv.org/abs/2305.18414
arXiv PDF paper https://arxiv.org/pdf/2305.18414.pdf
GitHub https://github.com/sunyx523/StEik
… present … (StEik) for learning implicit neural representations (INR) of shapes.
… popular eikonal loss … for … signed distance function constraint … approaches … limit that is unstable … fails to capture fine … structure.
… other terms added to the loss … can … eliminate … instabilities. However … can over-regularize … preventing … fine shape detail.
… introduce a new regularization term that still counteracts the eikonal instability but without over-regularizing.
… stabilization … allows for … new network structures … able to represent finer shape detail … based on quadratic layers.
… new regularization and network are able to capture more precise shape details and more accurate topology than existing state-of-the-art.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
