Abstract
Novel views synthesized from Neural Radiance Fields (NeRF) have reached remarkable rendering quality. However, a 5D radiance field volume is too large to be stored or directly rendered. In order to efficiently reconstruct and manipulate such a high-order tensor, we leverage inspirations from previous tensor decomposition methods, e.g. Tensorial Radiance Fields (TensoRF) and Hierarchical Tucker decomposition. And we propose a Hierarchical Vector-Matrix decomposition (HVMD) framework to learn a sparse approximation of high-order tensors. The proposed HVMD takes advantage of tensor separation and factorization properties and builds a hierarchical scheme that enables a better approximation of the high-order tensor with a very limited number of parameters. Our method achieves better-rendering quality than TensoRF in the NeRF-synthetic dataset given the same model size. The advantage gets more significant when the network parameter number becomes extremely small.
Original language | English |
---|---|
Title of host publication | 2023 IEEE International Conference on Multimedia and Expo (ICME) |
Publisher | IEEE |
Pages | 2183-2188 |
Number of pages | 6 |
ISBN (Electronic) | 9781665468916 |
ISBN (Print) | 9781665468923 |
DOIs | |
Publication status | Published - Jul 2023 |
Event | 2023 IEEE International Conference on Multimedia and Expo, ICME 2023 - Brisbane Convention & Exhibition Centre, Brisbane, Australia Duration: 10 Jul 2023 → 14 Jul 2023 https://www.2023.ieeeicme.org/index.php https://www.2023.ieeeicme.org/program.php https://ieeexplore.ieee.org/xpl/conhome/10219544/proceeding |
Publication series
Name | IEEE International Conference on Multimedia and Expo (ICME) |
---|
Conference
Conference | 2023 IEEE International Conference on Multimedia and Expo, ICME 2023 |
---|---|
Country/Territory | Australia |
City | Brisbane |
Period | 10/07/23 → 14/07/23 |
Internet address |