A 3D video scanner for face performance capture

Christchurch（2008）

引用 5|浏览1

暂无评分

摘要

This paper presents a 3D video scanner design for human face performance capture by active illumination stereo vision, combining a computational stereo algorithm with pattern projection to add texture to the scene. The scanner uses monochromatic video cameras to capture stereo images - a solution to obtain colour information was found by using a third web-camera and knowledge of the camera geometry to synthesise colour texture maps. Experimental results successfully demonstrate a proof of concept for an entirely computer vision based approach. The generated 3D video data being rendered and displayed using a standard graphics API yields highly realistic 3D face animation.

查看译文

关键词

computer animation,computer vision,face recognition,stereo image processing,video cameras,3d face animation,3d video scanner,active illumination stereo vision,colour information,computational stereo algorithm,face performance capture,graphics api,monochromatic video cameras,pattern projection,3d video,face animation,face reconstruction,scanner,stereo vision,texture mapping,lighting,face,proof of concept

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要