Get 3D object shape by aligning grids with the object surface normal with Gaur
Get 3D object shape by aligning grids with the object surface normal with Gaur
Oriented-grid Encoder for 3D Implicit Representations
arXiv paper abstract https://arxiv.org/abs/2402.06752
arXiv PDF paper https://arxiv.org/pdf/2402.06752.pdf
Encoding 3D points is one of the primary steps in learning-based implicit scene representation.
... prior techniques do not exploit some characteristics of most objects or scenes, such as surface normals and local smoothness.
This paper is the first to exploit those 3D characteristics in 3D geometric encoders explicitly.
... propose 3D-oriented grids with a novel cylindrical volumetric interpolation for modeling local planar invariance.
... explicitly include a local feature aggregation for feature regularization and smoothing of the cylindrical interpolation features.
... geometric encoder is shown to converge in fewer steps and obtain sharper 3D surfaces ... method gets state-of-the-art results.
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