FIELD: computer technology.
SUBSTANCE: invention relates to the field of computer technology for image processing. An input is received, containing an octree, which is a three-dimensional shape, nodes of the octree include empty nodes and non-empty nodes, wherein empty nodes exclude the three-dimensional shape and are leaf nodes of the octree, and non-empty nodes include part of the three-dimensional shape; and for nodes in the octree with depth d associated with a convolution layer of a convolutional neural network, the convolution operation of the mentioned convolution layer is performed to obtain an output of this convolution layer, wherein the output contains a map of three-dimensional shape features obtained by performing the convolution operation on nodes with d-depth in the input.
EFFECT: acceleration of the display of a three-dimensional shape/graphics in real time.
15 cl, 9 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD FOR AUTOMATIC CLASSIFICATION OF X-RAY IMAGES USING TRANSPARENCY MASKS | 2019 |
|
RU2716914C1 |
| METHOD AND DEVICE FOR ENCODING POINT CLOUD | 2020 |
|
RU2799041C1 |
| METHOD FOR DETECTING OBJECTS IN THE IMAGE OF THE PLAN-SCHEME OF THE CONSTRUCTION OBJECT | 2022 |
|
RU2785821C1 |
| METHOD OF TRAINING DEEP NEURAL NETWORKS BASED ON DISTRIBUTIONS OF PAIRWISE SIMILARITY MEASURES | 2016 |
|
RU2641447C1 |
| METHOD OF RECOGNIZING SPEECH EMOTIONS USING 3D CONVOLUTIONAL NEURAL NETWORK | 2023 |
|
RU2816680C1 |
| METHOD AND ELECTRONIC DEVICE FOR DETECTING THREE-DIMENSIONAL OBJECTS USING NEURAL NETWORKS | 2021 |
|
RU2776814C1 |
| IMAGE PROCESSING METHOD, TRAINING METHOD AND APPARATUS | 2021 |
|
RU2773420C1 |
| FAST CALCULATION OF CONVOLUTIONAL NEURAL NETWORK | 2018 |
|
RU2722473C1 |
| METHOD FOR PROVIDING COMPUTER VISION | 2022 |
|
RU2791587C1 |
| METHOD OF FORMATION OF NEURAL NETWORK ARCHITECTURE FOR CLASSIFICATION OF OBJECT TAKEN IN CLOUD OF POINTS, METHOD OF ITS APPLICATION FOR TEACHING NEURAL NETWORK AND SEARCHING SEMANTICALLY ALIKE CLOUDS OF POINTS | 2017 |
|
RU2674326C2 |
