Lagrangian Hashing for Compressed Neural Field Representations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910595293380608 |
|---|---|
| author | Govindarajan, Shrisudhan Sambugaro, Zeno Akhmedkhan Shabanov Takikawa, Towaki Rebain, Daniel Sun, Weiwei Conci, Nicola Yi, Kwang Moo Tagliasacchi, Andrea |
| author_facet | Govindarajan, Shrisudhan Sambugaro, Zeno Akhmedkhan Shabanov Takikawa, Towaki Rebain, Daniel Sun, Weiwei Conci, Nicola Yi, Kwang Moo Tagliasacchi, Andrea |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05334 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lagrangian Hashing for Compressed Neural Field Representations Govindarajan, Shrisudhan Sambugaro, Zeno Akhmedkhan Shabanov Takikawa, Towaki Rebain, Daniel Sun, Weiwei Conci, Nicola Yi, Kwang Moo Tagliasacchi, Andrea Computer Vision and Pattern Recognition 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. |
| title | Lagrangian Hashing for Compressed Neural Field Representations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.05334 |