WavePlanes: Compact Hex Planes for Dynamic Novel View Synthesis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916539281702912 |
|---|---|
| author | Azzarelli, Adrian Anantrasirichai, Nantheera Bull, David R |
| author_facet | Azzarelli, Adrian Anantrasirichai, Nantheera Bull, David R |
| contents | Dynamic Novel View Synthesis (Dynamic NVS) enhances NVS technologies to model moving 3-D scenes. However, current methods are resource intensive and challenging to compress. To address this, we present WavePlanes, a fast and more compact hex plane representation, applicable to both Neural Radiance Fields and Gaussian Splatting methods. Rather than modeling many feature scales separately (as done previously), we use the inverse discrete wavelet transform to reconstruct features at varying scales. This leads to a more compact representation and allows us to explore wavelet-based compression schemes for further gains. The proposed compression scheme exploits the sparsity of wavelet coefficients, by applying hard thresholding to the wavelet planes and storing nonzero coefficients and their locations on each plane in a Hash Map. Compared to the state-of-the-art (SotA), WavePlanes is significantly smaller, less resource demanding and competitive in reconstruction quality. Compared to small SotA models, WavePlanes outperforms methods in both model size and quality of novel views. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_02218 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | WavePlanes: Compact Hex Planes for Dynamic Novel View Synthesis Azzarelli, Adrian Anantrasirichai, Nantheera Bull, David R Computer Vision and Pattern Recognition Graphics Dynamic Novel View Synthesis (Dynamic NVS) enhances NVS technologies to model moving 3-D scenes. However, current methods are resource intensive and challenging to compress. To address this, we present WavePlanes, a fast and more compact hex plane representation, applicable to both Neural Radiance Fields and Gaussian Splatting methods. Rather than modeling many feature scales separately (as done previously), we use the inverse discrete wavelet transform to reconstruct features at varying scales. This leads to a more compact representation and allows us to explore wavelet-based compression schemes for further gains. The proposed compression scheme exploits the sparsity of wavelet coefficients, by applying hard thresholding to the wavelet planes and storing nonzero coefficients and their locations on each plane in a Hash Map. Compared to the state-of-the-art (SotA), WavePlanes is significantly smaller, less resource demanding and competitive in reconstruction quality. Compared to small SotA models, WavePlanes outperforms methods in both model size and quality of novel views. |
| title | WavePlanes: Compact Hex Planes for Dynamic Novel View Synthesis |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2312.02218 |