ReFiNe: Recursive Field Networks for Cross-modal Multi-scene Representation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914827867258880 |
|---|---|
| author | Zakharov, Sergey Liu, Katherine Gaidon, Adrien Ambrus, Rares |
| author_facet | Zakharov, Sergey Liu, Katherine Gaidon, Adrien Ambrus, Rares |
| contents | The common trade-offs of state-of-the-art methods for multi-shape representation (a single model "packing" multiple objects) involve trading modeling accuracy against memory and storage. We show how to encode multiple shapes represented as continuous neural fields with a higher degree of precision than previously possible and with low memory usage. Key to our approach is a recursive hierarchical formulation that exploits object self-similarity, leading to a highly compressed and efficient shape latent space. Thanks to the recursive formulation, our method supports spatial and global-to-local latent feature fusion without needing to initialize and maintain auxiliary data structures, while still allowing for continuous field queries to enable applications such as raytracing. In experiments on a set of diverse datasets, we provide compelling qualitative results and demonstrate state-of-the-art multi-scene reconstruction and compression results with a single network per dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04309 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReFiNe: Recursive Field Networks for Cross-modal Multi-scene Representation Zakharov, Sergey Liu, Katherine Gaidon, Adrien Ambrus, Rares Computer Vision and Pattern Recognition Graphics Machine Learning Multimedia The common trade-offs of state-of-the-art methods for multi-shape representation (a single model "packing" multiple objects) involve trading modeling accuracy against memory and storage. We show how to encode multiple shapes represented as continuous neural fields with a higher degree of precision than previously possible and with low memory usage. Key to our approach is a recursive hierarchical formulation that exploits object self-similarity, leading to a highly compressed and efficient shape latent space. Thanks to the recursive formulation, our method supports spatial and global-to-local latent feature fusion without needing to initialize and maintain auxiliary data structures, while still allowing for continuous field queries to enable applications such as raytracing. In experiments on a set of diverse datasets, we provide compelling qualitative results and demonstrate state-of-the-art multi-scene reconstruction and compression results with a single network per dataset. |
| title | ReFiNe: Recursive Field Networks for Cross-modal Multi-scene Representation |
| topic | Computer Vision and Pattern Recognition Graphics Machine Learning Multimedia |
| url | https://arxiv.org/abs/2406.04309 |