公开(公告)号：US10897609B2

公开(公告)日：2021-01-19

申请号：US16680474

申请日：2019-11-11

Applicant: Google LLC

Inventor： Jonathan Tilton Barron ,  Stephen Joseph DiVerdi ,  Ryan Geiss

IPC: H04N13/239 ,  G06T7/38 ,  H04N5/235 ,  G06T5/00 ,  G06T7/30 ,  H04N13/271 ,  H04N13/25 ,  G06K9/62 ,  G06T5/10 ,  H04N9/09 ,  G06T7/269 ,  G06T7/292 ,  H04N13/00

Abstract: The present disclosure relates to methods and systems that may improve and/or modify images captured using multiscopic image capture systems. In an example embodiment, burst image data is captured via a multiscopic image capture system. The burst image data may include at least one image pair. The at least one image pair is aligned based on at least one rectifying homography function. The at least one aligned image pair is warped based on a stereo disparity between the respective images of the image pair. The warped and aligned images are then stacked and a denoising algorithm is applied. Optionally, a high dynamic range algorithm may be applied to at least one output image of the aligned, warped, and denoised images.

公开(公告)号：US11800235B2

公开(公告)日：2023-10-24

申请号：US17629992

申请日：2019-08-19

Applicant: GOOGLE LLC

Inventor： Ryan Geiss ,  Marc S. Levoy ,  Samuel William Hasinoff ,  Tianfan Xue

IPC: H04N23/73 ,  G06F3/04847

CPC classification number: H04N23/73 ,  G06F3/04847

Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. A neural network can be trained to apply a lighting model to an input image. The training of the neural network can utilize confidence learning that is based on light predictions and prediction confidence values associated with lighting of the input image. A computing device can receive an input image of an object and data about a particular lighting model to be applied to the input image. The computing device can determine an output image of the object by using the trained neural network to apply the particular lighting model to the input image of the object.