Lagrangian Hashing for Compressed Neural Field Representations
Abstract
We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e. InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeRF). We achieve this by incorporating a point-based representation into the high-resolution layers of the hierarchical hash tables of an InstantNGP representation. As our points are equipped with a field of influence, our representation can be interpreted as a mixture of Gaussians stored within the hash table. We propose a loss that encourages the movement of our Gaussians towards regions that require more representation budget to be sufficiently well represented. Our main finding is that our representation allows the reconstruction of signals using a more compact representation without compromising quality.
Cite
Text
Govindarajan et al. "Lagrangian Hashing for Compressed Neural Field Representations." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73383-3_11Markdown
[Govindarajan et al. "Lagrangian Hashing for Compressed Neural Field Representations." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/govindarajan2024eccv-lagrangian/) doi:10.1007/978-3-031-73383-3_11BibTeX
@inproceedings{govindarajan2024eccv-lagrangian,
title = {{Lagrangian Hashing for Compressed Neural Field Representations}},
author = {Govindarajan, Shrisudhan and Sambugaro, Zeno and Shabanov, Akhmedkhan and Takikawa, Towaki and Sun, Weiwei and Rebain, Daniel and Conci, Nicola and Yi, Kwang Moo and Tagliasacchi, Andrea},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-73383-3_11},
url = {https://mlanthology.org/eccv/2024/govindarajan2024eccv-lagrangian/}
}