METHOD FOR CREATION OF MULTILAYERED SCENE REPRESENTATION AND COMPUTER DEVICE FOR ITS IMPLEMENTATION Russian patent published in 2023 - IPC G06T7/00 

Abstract RU 2787928 C1

FIELD: computer technology.

SUBSTANCE: present invention relates to a method and a device for creation of a multilayered scene representation. In the method, a pair of scene images is received, in which one image of the pair is considered as a reference image, and the other image of the pair is considered as an initial image; a reprojection operation is performed relatively to the pair of images for creation of a volume expanded on a plane; using a geometrical network Fg, a multilayered scene structure is predicted based on the volume expanded on the plane, and, using a color network Fc, color values and non-transparency values α are assessed for the predicted multilayered scene structure to obtain a multilayered scene representation; wherein, the geometrical network and the color network are trained in an end-to-end way, while the geometrical network is trained using at least geometrical loss calculated between the predicted multilayered structure and a real sparse point cloud corresponding to the scene in the reference image selected from a training video of a training dataset.

EFFECT: increase in the quality of new image synthesis.

16 cl, 14 dwg

Similar patents RU2787928C1

Title Year Author Number
METHOD FOR VISUALIZING A 3D PORTRAIT OF A PERSON WITH ALTERED LIGHTING AND A COMPUTING DEVICE FOR IT 2021
  • Sevastopolskij Artem Mikhajlovich
  • Lempitskij Viktor Sergeevich
RU2757563C1
METHOD FOR 3D RECONSTRUCTION OF A HUMAN HEAD TO OBTAIN A RENDER IMAGE OF A PERSON 2022
  • Khakhulin Taras Andreevich
  • Sklyarova Vanessa Valerievna
  • Lempitsky Victor Sergeevich
  • Zakharov Egor Olegovich
RU2786362C1
VISUALIZATION OF RECONSTRUCTION OF 3D SCENE USING SEMANTIC REGULARIZATION OF NORMALS TSDF WHEN TRAINING NEURAL NETWORK 2023
  • Sokolova Anna Ilyinichna
  • Vorontsova Anna Borisovna
  • Limonov Alexander Georgievich
RU2825722C1
RAPID TWO-LAYER NEURAL NETWORK SYNTHESIS OF REALISTIC IMAGES OF A NEURAL AVATAR BASED ON A SINGLE IMAGE 2020
  • Zakharov Egor Olegovich
  • Ivakhnenko Aleksei Aleksandrovich
  • Shysheya Aliaksandra Petrovna
  • Lempitsky Victor Sergeevich
RU2764144C1
METHOD OF CREATING FULL-LENGTH ANIMATED AVATAR OF PERSON FROM ONE IMAGE OF PERSON, COMPUTING DEVICE AND MACHINE-READABLE MEDIUM FOR IMPLEMENTATION THEREOF 2023
  • Svitov David Viacheslavovich
  • Gudkov Dmitrii Iurevich
  • Bashirov Renat Maratovich
  • Lempitsky Victor Sergeevich
RU2813485C1
METHOD FOR CONSTRUCTING A SCENE REPRESENTATION WITH DIRECT CORRECTION FOR REAL-TIME IMAGE SYNTHESIS 2022
  • Solovev Pavel Ilyich
  • Korzhenkov Denis Mikhailovich
  • Khakhulin Taras Andreevich
RU2799237C1
METHOD FOR PROVIDING COMPUTER VISION 2022
  • Rukhovich Danila Dmitrievich
  • Konushin Anton Sergeevich
  • Konushin Anton Sergeevich
RU2791587C1
IMAGE GENERATORS WITH CONDITIONALLY INDEPENDENT PIXEL SYNTHESIS 2021
  • Anokhin Ivan Aleksandrovich
  • Demochkin Kirill Vladislavovich
  • Khakhulin Taras Andreevich
  • Sterkin Gleb Mikhailovich
  • Lempitsky Victor Sergeevich
  • Korzhenkov Denis Mikhailovich
RU2770132C1
MODELLING PEOPLE'S CLOTHING BASED ON MULTIPLE POINTS 2021
  • Grigorev Artur Andreevich
  • Lempitsky Victor Sergeevich
  • Zakharkin Ilya Dmitrievich
  • Mazur Kirill Yevgenevich
RU2776825C1
NEURAL DOT GRAPHIC 2019
  • Aliev Kara-Ali Alibulatovich
  • Ulyanov Dmitry Vladimirovich
  • Lempitsky Victor Sergeevich
RU2729166C1

RU 2 787 928 C1

Authors

Sterkin Gleb Mikhaylovich

Solovev Pavel Ilyich

Korzhenkov Denis Mikhaylovich

Lempitsky Victor Sergeevich

Khakhulin Taras Andreevich

Dates

2023-01-13Published

2021-07-20Filed