Speckle-based three-dimensional-face reconstruction method and device

Abstract

The invention discloses a speckle-based three-dimensional-face reconstruction method and device. The method and the device can reduce matching calculation quantity while image feature richness is improved, and realize synchronized improvement of three-dimensional-face reconstruction efficiency and reconstruction precision. The method comprises: inputting a plurality of speckle image pairs conforming to binocular stereo vision; carrying out polar line correction on the input speckle image pairs to enable corresponding matching points to be at the same horizontal lines; carrying out face detection on the speckle image pairs after polar line correction, and extracting region-of-interest image pairs of to-be-reconstructed faces; carrying out first matching processing on the region-of-interestimage pairs to obtain first parallax graphs; setting a matching point searching range according to parallax in the first parallax graphs, and carrying out second matching processing on the region-of-interest image pairs to obtain second parallax graphs; and generating corresponding three-dimensional point cloud data according to the second parallax graphs and camera calibration parameters to obtain the reconstructed three-dimensional faces.

Description

technical field [0001] The invention relates to the technical field of multi-eye stereo vision, in particular to a speckle-based three-dimensional face reconstruction method and equipment. Background technique [0002] At present, 3D data is widely used in aerospace, 3D printing, geographic mapping, face detection and many other fields. Real-time and accurate acquisition of space-time data has always been the core issue of 3D information collection and 3D scene reconstruction, and it is also a hot research direction in the field of computer geometry. [0003] 3D face modeling stems from Parke's pioneering research to generate realistic 3D faces by computer. Obtaining 3D face depth information is the basic prerequisite for reconstructing a high-precision 3D face model, and 3D face data can be collected through monocular or multi-eye cameras. [0004] Among them, the main application scenario of multi-eye stereo vision is to restore the two-dimensional projection image to a ...

AI Technical Summary

Problems solved by technology

The Chinese patent application with the application number 200910093767.2 discloses another 3D face reconstruction method, which uses the texture component of the face deformation model to fit the face texture, but the accuracy of the speckle image is still not high, and the generated model is different from the real one. There is a certain gap in the face

Existing 3D reconstruction technologies all have the technical problems of large amount of calculation and computational efficiency, slow reconstruction speed and low precision

Images