The traditional oriented FAST and rotated BRIEF（ORB） algorithm has problems of instability and repetition of keypoints and it does not possess scale invariance. In order to deal with these drawbacks, a modified ORB...The traditional oriented FAST and rotated BRIEF（ORB） algorithm has problems of instability and repetition of keypoints and it does not possess scale invariance. In order to deal with these drawbacks, a modified ORB（MORB） algorithm is proposed. In order to improve the precision of matching and tracking, this paper puts forward an MOK algorithm that fuses MORB and Kanade-Lucas-Tomasi（KLT）. By using Kalman, the object＇s state in the next frame is predicted in order to reduce the size of search window and improve the real-time performance of object tracking. The experimental results show that the MOK algorithm can accurately track objects with deformation or with background clutters, exhibiting higher robustness and accuracy on diverse datasets. Also, the MOK algorithm has a good real-time performance with the average frame rate reaching 90.8 fps.展开更多
As a popular kind of stylized face,cartoon faces have rich application scenarios.It is challenging to create personalized 3D cartoon faces directly from 2D real photos.Besides,in order to adapt to more application sce...As a popular kind of stylized face,cartoon faces have rich application scenarios.It is challenging to create personalized 3D cartoon faces directly from 2D real photos.Besides,in order to adapt to more application scenarios,automatic style editing,and animation of cartoon faces is also a crucial problem that is urgently needed to be solved in the industry,but has not yet had a perfect solution.To solve this problem,we first propose“3D face cartoonizer”,which can generate high-quality 3D cartoon faces with texture when fed into 2D facial images.We contribute the first 3D cartoon face hybrid dataset and a new training strategy which first pretrains our network with low-quality triplets in a reconstruction-then-generation manner,and then finetunes it with high-quality triplets in an adversarial manner to fully leverage the hybrid dataset.Besides,we implement style editing for 3D cartoon faces based on k-means,which can be easily achieved without retrain the neural network.In addition,we propose a new cartoon faces'blendshape generation method,and based on this,realize the expression animation of 3D cartoon faces,enabling more practical applications.Our dataset and code will be released for future research.展开更多
基金supported by the National Natural Science Foundation of China(61471194)the Fundamental Research Funds for the Central Universities+2 种基金the Science and Technology on Avionics Integration Laboratory and Aeronautical Science Foundation of China(20155552050)the CASC(China Aerospace Science and Technology Corporation) Aerospace Science and Technology Innovation Foundation Projectthe Nanjing University of Aeronautics And Astronautics Graduate School Innovation Base(Laboratory)Open Foundation Program(kfjj20151505)
文摘The traditional oriented FAST and rotated BRIEF（ORB） algorithm has problems of instability and repetition of keypoints and it does not possess scale invariance. In order to deal with these drawbacks, a modified ORB（MORB） algorithm is proposed. In order to improve the precision of matching and tracking, this paper puts forward an MOK algorithm that fuses MORB and Kanade-Lucas-Tomasi（KLT）. By using Kalman, the object＇s state in the next frame is predicted in order to reduce the size of search window and improve the real-time performance of object tracking. The experimental results show that the MOK algorithm can accurately track objects with deformation or with background clutters, exhibiting higher robustness and accuracy on diverse datasets. Also, the MOK algorithm has a good real-time performance with the average frame rate reaching 90.8 fps.
基金supported by the National Key R&D Program of China(No.2018YFA0704000)the Beijing Natural Science Foundation(No.M22024)+2 种基金the National Natural Science Foundation of China(No.62021002)the Key Research and Development Project of Tibet Autonomous Region(No.XZ202101ZY0019G)supported by the Institute for Brain and Cognitive Sciences,BNRist,Tsinghua University,BLBCI,and Beijing Municipal Education Commission.
文摘As a popular kind of stylized face,cartoon faces have rich application scenarios.It is challenging to create personalized 3D cartoon faces directly from 2D real photos.Besides,in order to adapt to more application scenarios,automatic style editing,and animation of cartoon faces is also a crucial problem that is urgently needed to be solved in the industry,but has not yet had a perfect solution.To solve this problem,we first propose“3D face cartoonizer”,which can generate high-quality 3D cartoon faces with texture when fed into 2D facial images.We contribute the first 3D cartoon face hybrid dataset and a new training strategy which first pretrains our network with low-quality triplets in a reconstruction-then-generation manner,and then finetunes it with high-quality triplets in an adversarial manner to fully leverage the hybrid dataset.Besides,we implement style editing for 3D cartoon faces based on k-means,which can be easily achieved without retrain the neural network.In addition,we propose a new cartoon faces'blendshape generation method,and based on this,realize the expression animation of 3D cartoon faces,enabling more practical applications.Our dataset and code will be released for future research.
