HyperCube: Implicit Field Representations of Voxelized 3D Models (Student Abstract)

Magdalena Proszewska, Marcin Mazur, Tomasz Trzcinski, Przemyslaw Spurek

AAAI 2024 pp. 23623-23625

doi:10.1609/AAAI.V38I21.30499 /aaai/2024/proszewska2024aaai-hypercube/

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.

PDF AAAI Semantic Scholar

Cite

Text

Proszewska et al. "HyperCube: Implicit Field Representations of Voxelized 3D Models (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30499

Markdown

[Proszewska et al. "HyperCube: Implicit Field Representations of Voxelized 3D Models (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/proszewska2024aaai-hypercube/) doi:10.1609/AAAI.V38I21.30499

BibTeX

@inproceedings{proszewska2024aaai-hypercube,
  title     = {{HyperCube: Implicit Field Representations of Voxelized 3D Models (Student Abstract)}},
  author    = {Proszewska, Magdalena and Mazur, Marcin and Trzcinski, Tomasz and Spurek, Przemyslaw},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23623-23625},
  doi       = {10.1609/AAAI.V38I21.30499},
  url       = {https://mlanthology.org/aaai/2024/proszewska2024aaai-hypercube/}
}