Creative Scientism Lovers
做最有趣的技术,啃最硬的骨头
目标跟踪
手机端民用级别的跟踪算法通用型高但精度低,在对低频特征的运动目标及轮廓推断方面无法满足高精度需求,我们提出了一种工业级高精度跟踪算法,实现了低频特征的高精度跟踪。
软体仿真
我们研发的软体物理引擎TiSSUE基于非线性有限元实现,对生物软组织的仿真完全符合解剖学,我们从内到外建立软体模型,计算软体变形后,再推算皮肤的形变,最终产生表情,实现高度仿真的效果完全Phsically Correct。
人脸重建
手机端民用级别的人脸重建基于普通3DMM理论,无法满足工业应用场景对人脸重建精度的要求,我们提出了一种10万-100万点云级别高精度3DMM重建算法,精度是手机端算法的10-100倍。
Papers Publication
High-Quality Real Time Facial Capture Based on Single Camera 15 Nov 2021
Hongwei Xu, Leijia Dai, Jianxing Fu, Xiangyuan Wang, Quanwei Wang
We propose a real time deep learning framework for video-based facial expression capture. Our process uses a high-end facial capture pipeline based on FACEGOOD to capture facial expression. We train a convolutional neural network to produce high-quality continuous blendshape weight output from video training. Since this facial capture is fully automated, our system can drastically reduce the amount of labor involved in the development of modern narrative-driven video games or films involving realistic digital doubles of actors and potentially hours of animated dialogue per character. We demonstrate compelling animation inference in challenging areas such as eyes and lips.
https://arxiv.org/abs/2111.07556v1