公开(公告)号：US20230401815A1

公开(公告)日：2023-12-14

申请号：US17806410

申请日：2022-06-10

Applicant: Lemon Inc.

Inventor： Celong Liu ,  Lelin Zhang ,  Qingyu Chen ,  Yunzhu Li ,  Haoze Li ,  Xing Mei

IPC: G06V10/40 ,  G06V10/82 ,  G06V10/56

CPC classification number: G06V10/513 ,  G06V10/82 ,  G06V10/56

Abstract: A computer-implemented method for transforming a neural radiance field model is described. A plurality of inputs are provided 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. A spectral analysis is performed 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. Frequency components of the spectral analysis that represent colors for at least some of the voxels are extracted. A sparse volume data structure that represents the 3-dimensional space and the respective colors for the at least some of the voxels is generated.

公开(公告)号：US12190558B2

公开(公告)日：2025-01-07

申请号：US17806410

申请日：2022-06-10

Applicant: Lemon Inc.

Inventor： Celong Liu ,  Lelin Zhang ,  Qingyu Chen ,  Yunzhu Li ,  Haoze Li ,  Xing Mei

IPC: G06V10/40 ,  G06V10/56 ,  G06V10/82

Abstract: A computer-implemented method for transforming a neural radiance field model is described. A plurality of inputs are provided 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. A spectral analysis is performed 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. Frequency components of the spectral analysis that represent colors for at least some of the voxels are extracted. A sparse volume data structure that represents the 3-dimensional space and the respective colors for the at least some of the voxels is generated.