FIELD: computer vision.
SUBSTANCE: claimed solution accepts a set of images of the same scene taken by different cameras; gets feature tensors for each image; constructs a plane sweep volume (PSV) by concatenating the obtained feature tensors in the PSV depth direction using the received internal and external camera parameters; performing multiplanar imaging (MPI); gets MPI with RGBA texture; calculates differences between corresponding images from the received image set and corresponding images from the image set obtained from the MPI with the RGBA texture using an error function; performs the PSV construction by concatenating the calculated differences in the PSV depth direction; updating the MPI by aggregating the MPI features and the current PSV features.
EFFECT: increased speed and quality of image processing.
8 cl, 9 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR CREATION OF MULTILAYERED SCENE REPRESENTATION AND COMPUTER DEVICE FOR ITS IMPLEMENTATION | 2021 |
|
RU2787928C1 |
METHOD OF SYNTHESIS OF A TWO-DIMENSIONAL IMAGE OF A SCENE VIEWED FROM A REQUIRED VIEW POINT AND ELECTRONIC COMPUTING APPARATUS FOR IMPLEMENTATION THEREOF | 2020 |
|
RU2749749C1 |
METHOD OF CREATING FULL-LENGTH ANIMATED AVATAR OF PERSON FROM ONE IMAGE OF PERSON, COMPUTING DEVICE AND MACHINE-READABLE MEDIUM FOR IMPLEMENTATION THEREOF | 2023 |
|
RU2813485C1 |
METHOD FOR VISUALIZING A 3D PORTRAIT OF A PERSON WITH ALTERED LIGHTING AND A COMPUTING DEVICE FOR IT | 2021 |
|
RU2757563C1 |
NEURAL DOT GRAPHIC | 2019 |
|
RU2729166C1 |
DEVICE FOR CREATION OF MULTIDIMENSIONAL VIRTUAL IMAGES OF HUMAN RESPIRATORY ORGANS AND METHOD FOR CREATION OF VOLUMETRIC IMAGES, USING DEVICE | 2021 |
|
RU2783364C1 |
METHOD AND ELECTRONIC DEVICE FOR DETECTING THREE-DIMENSIONAL OBJECTS USING NEURAL NETWORKS | 2021 |
|
RU2776814C1 |
RAPID TWO-LAYER NEURAL NETWORK SYNTHESIS OF REALISTIC IMAGES OF A NEURAL AVATAR BASED ON A SINGLE IMAGE | 2020 |
|
RU2764144C1 |
VISUALIZATION OF RECONSTRUCTION OF 3D SCENE USING SEMANTIC REGULARIZATION OF NORMALS TSDF WHEN TRAINING NEURAL NETWORK | 2023 |
|
RU2825722C1 |
METHOD FOR PROVIDING COMPUTER VISION | 2022 |
|
RU2791587C1 |
Authors
Dates
2023-07-04—Published
2022-06-10—Filed