UE (Unreal Engine)-based performance capture system without marker

Abstract

The invention relates to the field of image processing, provides a UE (Unreal Engine)-based performance capture system without a marker, and aims to solve the problem that in methods of simultaneouslycapturing actions and expressions of performers to generate character animations, marker points cause intrusive feeling on the performers, and interference is enabled to be on performance. The systemincludes: a facial-performance capturing module, which is configured to collect facial image data of a performer, and calculate weight parameters of a facial expression of the performer according tothe facial image data; an action performance capturing module, which is configured to collect bone image data of the above performer, and determine human body posture parameters of the above performeraccording to the bone image data; and an animation generation module, which is configured to utilize a UE graphics program to generate an action and an expression of a character 3D model according tothe weight parameters of the above facial expression and the above human body posture parameters. The system realizes capturing of performer actions and expressions, and gives a virtual character realistic and reasonable actions and vivid expressions according to action and expression data.

Description

technical field [0001] The invention relates to the fields of computer graphics, computer vision and virtual reality, in particular to a UE engine-based unmarked performance capture system. Background technique [0002] Performance capture technology is used to capture the movements and expressions of performers, and has a wide range of applications in movies, animations, games and other fields. Through the performance capture technology, the virtual characters can be endowed with real and reasonable movements and vivid expressions, which can bring users a better viewing experience. Motion capture technology includes optical capture and inertial navigation capture. Optical capture uses an optical camera to photograph the performer, analyzes and calculates the joint points of the performer, such as kinect, etc.; inertial navigation capture obtains the motion state of the joint points through the sensors worn by the performer, and analyzes the current posture of the performer...

AI Technical Summary

Problems solved by technology

But the markers are intrusive to the performer, making it more difficult to perform naturally

Or, expression capture and motion capture are carried out separately, and then synthesized, but it increases the difficulty of combining each other in post-production, and restricts users to edit other characters

Images