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
... 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.
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
Comments