Converting neural radiance fields to 3d gaussians
AssigneeNVIDIA Corporation
InventorsKaiwen JIANG, Koki NAGANO, Shalini DE MELLO, Michael STENGEL
Life of this patent
Estimating the term…
Loading patent…
AssigneeNVIDIA Corporation
InventorsKaiwen JIANG, Koki NAGANO, Shalini DE MELLO, Michael STENGEL
Estimating the term…
Converting neural radiance fields to three-dimensional (3D) Gaussians includes receiving multi-view images, projecting camera rays through each of the multi-view images, generating first 3D points by sampling each of the camera rays, generating first five-dimensional (5D) input coordinates from the first 3D points and a corresponding two-dimensional (2D) viewing direction, processing the first 5D input coordinates using a neural network to generate first 3D Gaussians, generating second 3D points by sampling each of the camera rays, generating second 5D input coordinates from the second 3D points and the corresponding 2D viewing direction, processing the second 5D input coordinates using the neural network to generate second 3D Gaussians, and pruning the first 3D Gaussians summed with the second 3D Gaussians.
A computer-implemented method for converting a neural radiance field to a plurality of three-dimensional (3D) Gaussians, the method comprising:
One or more non-transitory computer-readable media storing instructions that, when executed by at least one processor, cause the at least one processor to perform the steps of:
A system, comprising:
Dependencies are inferred from the claim text.