250 citations · 430 across the 9 of their papers we have counts for
8 papers · 1 filter
Blendshapes GHUM: Real-time Monocular Facial Blendshape Prediction
Ivan Grishchenko, Geng Yan, Eduard Gabriel Bazavan +5
We present Blendshapes GHUM, an on-device ML pipeline that predicts 52 facial blendshape coefficients at 30+ FPS on modern mobile phones, from a single monocular RGB image and enab…
Efficient Heterogeneous Video Segmentation at the Edge
Jamie Menjay Lin, Siargey Pisarchyk, Juhyun Lee +7
We introduce an efficient video segmentation system for resource-limited edge devices leveraging heterogeneous compute. Specifically, we design network models by searching across m…
BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation
Ivan Grishchenko, Valentin Bazarevsky, Andrei Zanfir +7
We present BlazePose GHUM Holistic, a lightweight neural network pipeline for 3D human body landmarks and pose estimation, specifically tailored to real-time on-device inference. B…
Real-time Pupil Tracking from Monocular Video for Digital Puppetry
Artsiom Ablavatski, Andrey Vakunov, Ivan Grishchenko +2
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 ti…
Attention Mesh: High-fidelity Face Mesh Prediction in Real-time
Ivan Grishchenko, Artsiom Ablavatski, Yury Kartynnik +2
We present Attention Mesh, a lightweight architecture for 3D face mesh prediction that uses attention to semantically meaningful regions. Our neural network is designed for real-ti…
BlazePose: On-device Real-time Body Pose tracking
Valentin Bazarevsky, Ivan Grishchenko, Karthik Raveendran +3
We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference…
BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs
Valentin Bazarevsky, Yury Kartynnik, Andrey Vakunov +2
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-realtim…
Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction
Steven Hickson, Karthik Raveendran, Alireza Fathi +2
We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These ins…