Adobe Inc.

États‑Unis d’Amérique

Retour au propriétaire

1-2 de 2 pour Adobe Inc. Trier par
Recheche Texte
Brevet
International - WIPO
Excluant les filiales
Affiner par Reset Report
Classe IPC
G06T 1/40 - Réseaux neuronaux 1
G06T 15/50 - Effets de lumière 1
G06T 7/586 - Récupération de la profondeur ou de la forme à partir de plusieurs images à partir de plusieurs sources de lumière, p.ex. stéréophotométrie 1
Résultats pour  brevets

1.

DYNAMICALLY ESTIMATING LIGHT-SOURCE-SPECIFIC PARAMETERS FOR DIGITAL IMAGES USING A NEURAL NETWORK

      
Numéro d'application CA2020051194
Numéro de publication 2021/042208
Statut Délivré - en vigueur
Date de dépôt 2020-09-02
Date de publication 2021-03-11
Propriétaire
  • UNIVERSITÉ LAVAL (Canada)
  • ADOBE INC. (USA)
Inventeur(s)
  • Sunkavalli, Kalyan
  • Hold-Geoffroy, Yannick
  • Gagne, Christian
  • Gardner, Marc-Andre
  • Lalonde, Jean-Francois

Abrégé

This disclosure relates to methods, non-transitory computer readable media, and systems that can render a virtual object in a digital image by using a source-specific-lighting-estimation-neural network to generate three-dimensional ("3D") lighting parameters specific to a light source illuminating the digital image. To generate such source-specific-lighting parameters, for instance, the disclosed systems utilize a compact source-specific-lighting-estimation-neural network comprising both common network layers and network layers specific to different lighting parameters. In some embodiments, the disclosed systems further train such a source-specific-lighting-estimation-neural network to accurately estimate spatially varying lighting in a digital image based on comparisons of predicted environment maps from a differentiable-projection layer with ground-truth-environment maps.

Classes IPC  ?

2.

METHOD FOR DETERMINING A NORMAL MAP ON THE BASIS OF IMAGES BY MEANS OF UNCALIBRATED PHOTOMETRIC STEREO

      
Numéro d'application IB2020057044
Numéro de publication 2021/019414
Statut Délivré - en vigueur
Date de dépôt 2020-07-25
Date de publication 2021-02-04
Propriétaire ADOBE INC. (USA)
Inventeur(s) El Hajjar, Jean-François

Abrégé

Method for determining a normal map on the basis of a plurality of 2D images by means of uncalibrated photometric stereo, comprising the steps of: - receiving a set of images with various uncalibrated lighting conditions; - extracting a field of intermediate normals and a field of intermediate lights that result from decomposing the matrix I containing the image data into singular values; - determining six minor coefficients of the inverse of the linear transformation to be applied to field of normals in order to make it integrable; - modifying the field of normals in order to make its induced surface integrable; - extracting Lambertian diffuse reflectance maxima (LDRM); - determining the generalized bas-relief ambiguity based on the LDRM using a statistical approach; - applying the GBR to the fields of intermediate normals and of intermediate lights; - normalizing the normals of the field of intermediate normals.

Classes IPC  ?

  • G06T 7/586 - Récupération de la profondeur ou de la forme à partir de plusieurs images à partir de plusieurs sources de lumière, p.ex. stéréophotométrie