Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Vakunov, Andrey"'
Autor:
Ablavatski, Artsiom, Vakunov, Andrey, Grishchenko, Ivan, Raveendran, Karthik, Zhdanovich, Matsvei
We present a simple, real-time approach for pupil tracking from live video on mobile devices. Our method extends a state-of-the-art face mesh detector with two new components: a tiny neural network that predicts positions of the pupils in 2D, and a d
Externí odkaz:
http://arxiv.org/abs/2006.11341
Autor:
Zhang, Fan, Bazarevsky, Valentin, Vakunov, Andrey, Tkachenka, Andrei, Sung, George, Chang, Chuo-Ling, Grundmann, Matthias
We present a real-time on-device hand tracking pipeline that predicts hand skeleton from single RGB camera for AR/VR applications. The pipeline consists of two models: 1) a palm detector, 2) a hand landmark model. It's implemented via MediaPipe, a fr
Externí odkaz:
http://arxiv.org/abs/2006.10214
Autor:
Tkachenka, Andrei, Karpiak, Gregory, Vakunov, Andrey, Kartynnik, Yury, Ablavatski, Artsiom, Bazarevsky, Valentin, Pisarchyk, Siargey
We present a novel approach for neural network-based hair segmentation from a single camera input specifically designed for real-time, mobile application. Our relatively small neural network produces a high-quality hair segmentation mask that is well
Externí odkaz:
http://arxiv.org/abs/1907.06740
Autor:
Bazarevsky, Valentin, Kartynnik, Yury, Vakunov, Andrey, Raveendran, Karthik, Grundmann, Matthias
We present BlazeFace, a lightweight and well-performing face detector tailored for mobile GPU inference. It runs at a speed of 200-1000+ FPS on flagship devices. This super-realtime performance enables it to be applied to any augmented reality pipeli
Externí odkaz:
http://arxiv.org/abs/1907.05047