InterNeRF: Scaling Radiance Fields via Parameter Interpolation
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_ | 1866910491287224320 |
|---|---|
| author | Wang, Clinton Hedman, Peter Golland, Polina Barron, Jonathan T. Duckworth, Daniel |
| author_facet | Wang, Clinton Hedman, Peter Golland, Polina Barron, Jonathan T. Duckworth, Daniel |
| contents | Neural Radiance Fields (NeRFs) have unmatched fidelity on large, real-world scenes. A common approach for scaling NeRFs is to partition the scene into regions, each of which is assigned its own parameters. When implemented naively, such an approach is limited by poor test-time scaling and inconsistent appearance and geometry. We instead propose InterNeRF, a novel architecture for rendering a target view using a subset of the model's parameters. Our approach enables out-of-core training and rendering, increasing total model capacity with only a modest increase to training time. We demonstrate significant improvements in multi-room scenes while remaining competitive on standard benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11737 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InterNeRF: Scaling Radiance Fields via Parameter Interpolation Wang, Clinton Hedman, Peter Golland, Polina Barron, Jonathan T. Duckworth, Daniel Computer Vision and Pattern Recognition Graphics Neural Radiance Fields (NeRFs) have unmatched fidelity on large, real-world scenes. A common approach for scaling NeRFs is to partition the scene into regions, each of which is assigned its own parameters. When implemented naively, such an approach is limited by poor test-time scaling and inconsistent appearance and geometry. We instead propose InterNeRF, a novel architecture for rendering a target view using a subset of the model's parameters. Our approach enables out-of-core training and rendering, increasing total model capacity with only a modest increase to training time. We demonstrate significant improvements in multi-room scenes while remaining competitive on standard benchmarks. |
| title | InterNeRF: Scaling Radiance Fields via Parameter Interpolation |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2406.11737 |