PBR three-dimensional reconstruction method and system based on deep learning, and computer storage medium
A deep learning and three-dimensional reconstruction technology, applied in the field of three-dimensional reconstruction, can solve the problems of inability to restore texture information, low color and texture restoration, and achieve the effect of high-precision three-dimensional reconstruction and physical rendering
Active Publication Date: 2021-09-03
南京万生华态科技有限公司
View PDF5 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The main purpose of the traditional 3D reconstruction method is to restore the structural information of the object, and the restoration degree of the color texture is not high, especially the texture information based on the physical rendering standard in the field of computer graphics cannot be restored.
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
[0039] In order to better understand the technical content of the present invention, specific embodiments are given together with the attached drawings for description as follows.
[0040] Aspects of the invention are described in this disclosure with reference to the accompanying drawings, which show a number of illustrated embodiments. Embodiments of the present disclosure are not necessarily intended to include all aspects of the invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in more detail below, can be implemented in any of numerous ways, since the concepts and embodiments disclosed herein are not limited to any implementation. In addition, some aspects of the present disclosure may be used alone or in any suitable combination with other aspects of the present disclosure.
[0041] combine Figure 1-2 In the PBR 3D reconstruction method based on deep learning in the exemplary embodiment shown, on...
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 PBR three-dimensional reconstruction method based on deep learning, and the method comprises the following steps: obtaining a multi-angle picture of a three-dimensional object, and taking the multi-angle picture as a picture sequence; performing feature point matching on each photo in the photo sequence, and calculating camera internal parameters, camera external parameters and sparse point clouds corresponding to each photo; performing dense reconstruction to obtain dense point cloud and position information of each point in each photo; converting the dense point cloud into a grid model and an inherent color map; and constructing a deep learning neural network model based on back propagation by taking the vertexes of the grid model, the map coordinate points and surfaces and the inherent color map as initialization parameters, and when the deep learning neural network model converges, obtaining a network model and a texture map required by PBR three-dimensional reconstruction so as to realize PBR three-dimensional reconstruction.
Description
technical field [0001] The present invention relates to the technical field of three-dimensional reconstruction, in particular to a PBR three-dimensional reconstruction method, system and computer storage medium based on deep learning. Background technique [0002] 3D reconstruction (3D Reconstruction) technology refers to a method of restoring and representing three-dimensional objects in a computer, and is widely used in computer vision (CV, Computer Vision), computer graphics (CG, Computer Graphics), medical image processing, virtual reality, etc. field. [0003] 3D reconstruction technology, especially the dense 3D reconstruction of indoor scenes, hopes to use consumer-grade cameras to scan indoor scenes to achieve real-time dense 3D reconstruction. Traditional 3D reconstruction techniques usually include image acquisition, sparse reconstruction, dense reconstruction, and texture mapping to generate accurate and complete 3D models. Typically, people use a camera to tak...
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 IPC IPC(8): G06T15/04G06T17/00G06T7/80G06N3/08
CPCG06T15/04G06T17/00G06T7/85G06N3/08G06T2207/10012
Inventor 彭程张杰昊
Owner 南京万生华态科技有限公司