Lightplane: Highly-Scalable Components for Neural 3D Fields
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_ | 1866914777843892224 |
|---|---|
| author | Cao, Ang Johnson, Justin Vedaldi, Andrea Novotny, David |
| author_facet | Cao, Ang Johnson, Justin Vedaldi, Andrea Novotny, David |
| contents | Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are memory-intensive, posing a significant bottleneck for existing methods and hindering new applications. In response, we propose a pair of highly scalable components for 3D neural fields: Lightplane Render and Splatter, which significantly reduce memory usage in 2D-3D mapping. These innovations enable the processing of vastly more and higher resolution images with small memory and computational costs. We demonstrate their utility in various applications, from benefiting single-scene optimization with image-level losses to realizing a versatile pipeline for dramatically scaling 3D reconstruction and generation. Code: \url{https://github.com/facebookresearch/lightplane}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19760 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lightplane: Highly-Scalable Components for Neural 3D Fields Cao, Ang Johnson, Justin Vedaldi, Andrea Novotny, David Computer Vision and Pattern Recognition Graphics Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are memory-intensive, posing a significant bottleneck for existing methods and hindering new applications. In response, we propose a pair of highly scalable components for 3D neural fields: Lightplane Render and Splatter, which significantly reduce memory usage in 2D-3D mapping. These innovations enable the processing of vastly more and higher resolution images with small memory and computational costs. We demonstrate their utility in various applications, from benefiting single-scene optimization with image-level losses to realizing a versatile pipeline for dramatically scaling 3D reconstruction and generation. Code: \url{https://github.com/facebookresearch/lightplane}. |
| title | Lightplane: Highly-Scalable Components for Neural 3D Fields |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2404.19760 |