HyperCube: Implicit Field Representations of Voxelized 3D Models (Student Abstract)
Magdalena Proszewska, Marcin Mazur, Tomasz Trzciński, Przemysław Spurek
Abstract
Implicit field representations offer an effective way of generating 3D object shapes. They leverage an implicit decoder (IM-NET) trained to take a 3D point coordinate concatenated with a shape encoding and to output a value indicating whether the point is outside the shape. This approach enables the efficient rendering of visually plausible objects but also has some significant limitations, resulting in a cumbersome training procedure and empty spaces within the rendered mesh. In this paper, we introduce a new HyperCube architecture based on interval arithmetic that enables direct processing of 3D voxels, trained using a hypernetwork paradigm to enforce model convergence. The code is available at https://github.com/mproszewska/hypercube.
BibTeX
@article{Proszewska_Mazur_Trzciński_Spurek_2024, title={HyperCube: Implicit Field Representations of Voxelized 3D Models (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30499}, DOI={10.1609/aaai.v38i21.30499}, abstractNote={Implicit field representations offer an effective way of generating 3D object shapes. They leverage an implicit decoder (IM-NET) trained to take a 3D point coordinate concatenated with a shape encoding and to output a value indicating whether the point is outside the shape. This approach enables the efficient rendering of visually plausible objects but also has some significant limitations, resulting in a cumbersome training procedure and empty spaces within the rendered mesh. In this paper, we introduce a new HyperCube architecture based on interval arithmetic that enables direct processing of 3D voxels, trained using a hypernetwork paradigm to enforce model convergence. The code is available at https://github.com/mproszewska/hypercube.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Proszewska, Magdalena and Mazur, Marcin and Trzciński, Tomasz and Spurek, Przemysław}, year={2024}, month={Mar.}, pages={23623-23625} }