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

07/15/2019
by   Yury Kartynnik, et al.
0

We present an end-to-end neural network-based model for inferring an approximate 3D mesh representation of a human face from single camera input for AR applications. The relatively dense mesh model of 468 vertices is well-suited for face-based AR effects. The proposed model demonstrates super-realtime inference speed on mobile GPUs (100-1000+ FPS, depending on the device and model variant) and a high prediction quality that is comparable to the variance in manual annotations of the same image.

READ FULL TEXT

page 1

page 2

page 3

research
07/15/2019

Real-time Hair Segmentation and Recoloring on Mobile GPUs

We present a novel approach for neural network-based hair segmentation f...
research
06/19/2020

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

We present Attention Mesh, a lightweight architecture for 3D face mesh p...
research
06/18/2020

MediaPipe Hands: On-device Real-time Hand Tracking

We present a real-time on-device hand tracking pipeline that predicts ha...
research
07/11/2019

BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs

We present BlazeFace, a lightweight and well-performing face detector ta...
research
09/11/2023

Blendshapes GHUM: Real-time Monocular Facial Blendshape Prediction

We present Blendshapes GHUM, an on-device ML pipeline that predicts 52 f...
research
05/24/2023

Generative Adversarial Shaders for Real-Time Realism Enhancement

Application of realism enhancement methods, particularly in real-time an...

Please sign up or login with your details

Forgot password? Click here to reset