VISUALIZATION OF RECONSTRUCTION OF 3D SCENE USING SEMANTIC REGULARIZATION OF NORMALS TSDF WHEN TRAINING NEURAL NETWORK Russian patent published in 2024 - IPC G06N3/08 G06T17/00 G06T7/55 

Abstract RU 2825722 C1

FIELD: image processing.

SUBSTANCE: method for reconstruction of 3D scene and its visualization using a neural network consisting of a basic neural network, including a skeleton, which is the main part of the basic neural network, which calculates features, a TSDF head, which performs prediction of TSDF values in each voxel, and a segmentation head, which is 3D sparse convolutional segmentation module, which predicts the segmentation marks in each voxel, comprising steps of: basic neural network is trained to obtain TSDF volume for scene voxels as follows, training data is input, TSDF loss between TSDF prediction is calculated, calculating the segmentation loss between the segmentation prediction and the segmentation reference, calculating the coordinates of the normals, calculating the total loss function as the total loss function TSDF, minimizing the total loss function, using a trained basic neural network to obtain a TSDF volume of an input sequence of RGB frames of a real scene, applying an algorithm to the TSDF volume, which calculates reconstruction of 3D scene, 3D scene reconstruction is rendered to obtain 3D scene visualization.

EFFECT: high accuracy of reconstructing 3D scene.

11 cl, 2 dwg, 3 tbl

Similar patents RU2825722C1

Title Year Author Number
METHOD FOR PROVIDING COMPUTER VISION 2022
  • Rukhovich Danila Dmitrievich
  • Konushin Anton Sergeevich
  • Konushin Anton Sergeevich
RU2791587C1
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 AND ELECTRONIC DEVICE FOR DETECTING THREE-DIMENSIONAL OBJECTS USING NEURAL NETWORKS 2021
  • Rukhovich Danila Dmitrievich
  • Vorontsova Anna Borisovna
  • Konushin Anton Sergeevich
RU2776814C1
METHOD AND SYSTEM FOR REMOTE CLOTHING SELECTION 2020
  • Fedyukov Maxim Alexandrovich
  • Poskonin Andrey Vladimirovich
  • Klimentyev Sergey Mikhailovich
  • Guzov Vladimir Vladimirovich
  • Petrov Ilia Alexeevich
  • Koval Andrei Vasilievich
  • Patakin Nikolay
  • Fedotov Anton Vladimirovich
  • Korneev Oleg Vladimirovich
RU2805003C2
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 AND SYSTEM FOR REFINING THE CAMERA POSITION TAKING INTO ACCOUNT THE ROOM PLAN 2022
  • Sokolova Anna Ilyinichna
  • Limonov Alexander Georgievich
  • Nikitin Filipp Alexandrovich
  • Konushin Anton Sergeevich
RU2794441C1
NEURAL DOT GRAPHIC 2019
  • Aliev Kara-Ali Alibulatovich
  • Ulyanov Dmitry Vladimirovich
  • Lempitsky Victor Sergeevich
RU2729166C1
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
MODELLING PEOPLE'S CLOTHING BASED ON MULTIPLE POINTS 2021
  • Grigorev Artur Andreevich
  • Lempitsky Victor Sergeevich
  • Zakharkin Ilya Dmitrievich
  • Mazur Kirill Yevgenevich
RU2776825C1
NEURAL NETWORK TRANSFER OF THE FACIAL EXPRESSION AND POSITION OF THE HEAD USING HIDDEN POSITION DESCRIPTORS 2020
  • Burkov Egor Andreevich
  • Pasechnik Igor Igorevich
  • Lempitsky Victor Sergeevich
RU2755396C1

RU 2 825 722 C1

Authors

Sokolova Anna Ilyinichna

Vorontsova Anna Borisovna

Limonov Alexander Georgievich

Dates

2024-08-28Published

2023-08-24Filed