	US 12,190,558 B2
	View synthesis from sparse volume data structure
Celong Liu, Los Angeles, CA (US); Lelin Zhang, Los Angeles, CA (US); Qingyu Chen, Los Angeles, CA (US); Yunzhu Li, Los Angeles, CA (US); Haoze Li, Los Angeles, CA (US); and Xing Mei, Los Angeles, CA (US)
Assigned to Lemon Inc., Grand Cayman (KY)
Filed by Lemon Inc., Grand Cayman (KY)
Filed on Jun. 10, 2022, as Appl. No. 17/806,410.
Prior Publication US 2023/0401815 A1, Dec. 14, 2023
Int. Cl. G06V 10/40 (2022.01); G06V 10/56 (2022.01); G06V 10/82 (2022.01)

CPC G06V 10/513 (2022.01) [G06V 10/56 (2022.01); G06V 10/82 (2022.01)]

20 Claims

1. A computer-implemented method for transforming a neural radiance field model, the method comprising:

providing a plurality of inputs to a neural radiance field (NeRF) model that represents a 3-dimensional space having a subject, wherein each input of the plurality of inputs includes a location and a view direction and corresponds to respective colors of voxels that represent the 3-dimensional space;

performing a spectral analysis on a plurality of outputs of the NeRF model based on the plurality of inputs, wherein the plurality of outputs include the respective colors of the voxels;

extracting frequency components of the spectral analysis that represent colors for at least some of the voxels; and

generating a sparse volume data structure that represents the 3-dimensional space and the respective colors for the at least some of the voxels.