BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation

no code implementations • 23 Jun 2022 • Ivan Grishchenko, Valentin Bazarevsky, Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir, Richard Yee, Karthik Raveendran, Matsvei Zhdanovich, Matthias Grundmann, Cristian Sminchisescu

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.

3D Human Pose Estimation

Real-time Pupil Tracking from Monocular Video for Digital Puppetry

1 code implementation • 19 Jun 2020 • Artsiom Ablavatski, Andrey Vakunov, Ivan Grishchenko, Karthik Raveendran, Matsvei Zhdanovich

We present a simple, real-time approach for pupil tracking from live video on mobile devices.

Attention Mesh: High-fidelity Face Mesh Prediction in Real-time

1 code implementation • 19 Jun 2020 • Ivan Grishchenko, Artsiom Ablavatski, Yury Kartynnik, Karthik Raveendran, Matthias Grundmann

We present Attention Mesh, a lightweight architecture for 3D face mesh prediction that uses attention to semantically meaningful regions.

BlazePose: On-device Real-time Body Pose tracking

7 code implementations • 17 Jun 2020 • Valentin Bazarevsky, Ivan Grishchenko, Karthik Raveendran, Tyler Zhu, Fan Zhang, Matthias Grundmann

We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices.

3D Human Pose Estimation 3D Pose Estimation +3

Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs

3 code implementations • 15 Jul 2019 • Yury Kartynnik, Artsiom Ablavatski, Ivan Grishchenko, Matthias Grundmann

The relatively dense mesh model of 468 vertices is well-suited for face-based AR effects.

Face Reconstruction