Akhmedkhan Shabanov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Akhmedkhan Shabanov has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Andrea Tagliasacchi
Simon Fraser University, Burnaby, Canada; University of Toronto, Toronto, Canada and Wayve, Vancouver, Canada
2 shared publications - Daniel Rebain
University of British Columbia, Vancouver, Canada and Wayve, Vancouver, Canada
2 shared publications - Nicola Conci
Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy
2 shared publications - Shrisudhan Govindarajan
Simon Fraser University
2 shared publications - Towaki Takikawa
University of Toronto
2 shared publications - Zeno Sambugaro
University of Trento
2 shared publications
Latest Publications
- 3 November 2024
- Published by Springer Nature
- p. 183-199
Lagrangian Hashing for Compressed Neural Field Representations
- 3 November 2024
- Published by Springer Nature
- p. 183-199
Lagrangian Hashing for Compressed Neural Field Representations
- Open Access
Lagrangian Hashing for Compressed Neural Field Representations
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.
Open AccessLagrangian Hashing for Compressed Neural Field Representations
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.