公开(公告)号：US20250148567A1

公开(公告)日：2025-05-08

申请号：US18502736

申请日：2023-11-06

Applicant: Google LLC

Inventor： Keunhong Park ,  Ricardo Martin-Brualla ,  Jonathan Tilton Barron ,  Philipp Henzler ,  Benjamin Joseph Mildenhall

IPC: G06T3/00 ,  G06T7/00

Abstract: Systems and methods for training a machine-learned model are disclosed herein. The method can include obtaining, by a processor, a plurality of images, each image having a set of parameter values comprising values for a plurality of camera parameters and determining a covariance matrix for the plurality of camera parameters with respect to a plurality of projected points generated via evaluation of a projection function. The method can also include performing a whitening algorithm to identify a preconditioning matrix that, when applied to the sets of parameter values, results in the covariance matrix being approximately equal to an identity matrix and performing an optimization algorithm on the plurality of sets of parameter values, Performing the optimization algorithm can include applying an inverse of the preconditioning matrix to the plurality of sets of parameters in a forward prediction pass and applying the preconditioning matrix in a backward gradient pass.

公开(公告)号：US20240273811A1

公开(公告)日：2024-08-15

申请号：US18012270

申请日：2022-10-24

Applicant: Google LLC

Inventor： Noha Radwan ,  Jonathan Tilton Barron ,  Benjamin Joseph Mildenhall ,  Seyed Mohammad Mehdi Sajjadi ,  Michael Niemeyer

IPC: G06T15/20 ,  G06V10/82

CPC classification number: G06T15/205 ,  G06V10/82

Abstract: Systems and methods for training a neural radiance field model can include the use of image patches for ground truth training. For example, the systems and methods can include generating patch renderings with a neural radiance field model, comparing the patch renderings to ground truth patches from ground truth images, and adjusting one or more parameters based on the comparison. Additionally and/or alternatively, the systems and methods can include the utilization of a flow model for mitigating and/or minimizing artifact generation.

公开(公告)号：US20240320912A1

公开(公告)日：2024-09-26

申请号：US18611236

申请日：2024-03-20

Applicant: Google LLC

Inventor： Yuanzhen Li ,  Amit Raj ,  Varun Jampani ,  Benjamin Joseph Mildenhall ,  Benjamin Michael Poole ,  Jonathan Tilton Barron ,  Kfir Aberman ,  Michael Niemeyer ,  Michael Rubinstein ,  Nataniel Ruiz Gutierrez ,  Shiran Elyahu Zada ,  Srinivas Kaza

IPC: G06T17/00 ,  H04N13/279 ,  H04N13/351

CPC classification number: G06T17/00 ,  H04N13/279 ,  H04N13/351

Abstract: A fractional training process can be performed training images to an instance of a machine-learned generative image model to obtain a partially trained instance of the model. A fractional optimization process can be performed with the partially trained instance to an instance of a machine-learned three-dimensional (3D) implicit representation model obtain a partially optimized instance of the model. Based on the plurality of training images, pseudo multi-view subject images can be generated with the partially optimized instance of the 3D implicit representation model and a fully trained instance of the generative image model; The partially trained instance of the model can be trained with a set of training data. The partially optimized instance of the machine-learned 3D implicit representation model can be trained with the machine-learned multi-view image model.

公开(公告)号：US20250037244A1

公开(公告)日：2025-01-30

申请号：US18709218

申请日：2022-10-21

Applicant: Google LLC

Inventor： Benjamin Joseph Mildenhall ,  Pratul Preeti Srinivasan ,  Jonathan Tilton Barron ,  Richardo Martin-Brualla ,  Lars Peter Johannes Hedman

IPC: G06T5/60 ,  G06T5/50 ,  G06T5/70 ,  G06T5/92 ,  G06T15/20 ,  G06T19/20

Abstract: Systems and methods for training a neural radiance field model for noisy scenes can leverage raw noisy images in linear high dynamic range color space to train a neural radiance field model to generate view synthesis of low light and/or high contrast scenes. The trained model can then be utilized to accurately complete view rendering tasks without the preprocessing used for generating low dynamic range images. In some implementations, training on unprocessed data of a low light scene can allow for training a neural radiance field model to generate high quality view renderings of a low light scene.