Three-dimensional point cloud reconstruction method and device, electronic equipment and storage medium
A three-dimensional point cloud, three-dimensional technology, applied in the field of computer vision, can solve the problems of poor accuracy and integrity of three-dimensional point cloud
Pending Publication Date: 2021-07-23
SHANGHAI SENSETIME LINGANG INTELLIGENT TECH CO LTD
View PDF0 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, since the existing MVS matching schemes largely rely on the richness of image textures, for scenes with insufficient image textures such as roads and traffic signs (such as autonomous driving scenes), it is easy to leave holes and outliers. This leads to poor accuracy and completeness of the subsequently reconstructed 3D point cloud
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0090]In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only It is a part of the embodiments of the present disclosure, but not all of them. The components of the disclosed embodiments generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skil...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a three-dimensional point cloud reconstruction method and device, electronic equipment and a storage medium, and the method comprises the steps of obtaining three-dimensional sparse point cloud data determined based on each scene image shot from different shooting angles, and the semantic annotation information of each scene image in each scene image; based on the semantic annotation information of each scene image and the three-dimensional sparse point cloud data, generating a depth map corresponding to each scene image; and based on the depth map corresponding to each scene image, reconstructing a three-dimensional point cloud to obtain three-dimensional dense point cloud data. According to the invention, in the process of generating the depth map, the semantic annotation information is combined to better guide the point cloud reconstruction of the weak texture image area, so that the generated three-dimensional dense point cloud data is not liable to have holes, external points and other flaws, and the integrity is obviously improved on the premise of ensuring the precision of the reconstructed point cloud data.
Description
technical field [0001] The present disclosure relates to the technical field of computer vision, and in particular, to a method, device, electronic device and storage medium for three-dimensional point cloud reconstruction. Background technique [0002] 3D reconstruction technology is one of the important research directions in the field of computer vision, and its purpose is to recover the 3D point cloud information of scenes or objects from multiple images. With the rapid development of Structure From Motion (SFM) and Multiple Views Stereo (MVS), image-based 3D reconstruction of dense point clouds has received more and more attention. [0003] Among them, MVS matching, as an intermediate link in image-based 3D reconstruction, plays a role in generating dense point clouds. However, since the existing MVS matching schemes largely rely on the richness of image textures, for scenes with insufficient image textures such as roads and traffic signs (such as autonomous driving sc...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T17/20G06T7/73
CPCG06T17/20G06T7/73G06T2207/10028G06T2207/30244
Inventor 刘余钱申抒含吕明哲
Owner SHANGHAI SENSETIME LINGANG INTELLIGENT TECH CO LTD