• Home
  • Search
  • Stabilized real-time face tracking via a learned dynamic rigidity prior
  • Cite Icon42
  • https://doi.org/10.1145/3272127.3275093Copy DOI Icon

Stabilized real-time face tracking via a learned dynamic rigidity prior

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Despite the popularity of real-time monocular face tracking systems in many successful applications, one overlooked problem with these systems is rigid instability. It occurs when the input facial motion can be explained by either head pose change or facial expression change, creating ambiguities that often lead to jittery and unstable rigid head poses under large expressions. Existing rigid stabilization methods either employ a heavy anatomically-motivated approach that are unsuitable for real-time applications, or utilize heuristic-based rules that can be problematic under certain expressions. We propose the first rigid stabilization method for real-time monocular face tracking using a dynamic rigidity prior learned from realistic datasets. The prior is defined on a region-based face model and provides dynamic region-based adaptivity for rigid pose optimization during real-time performance. We introduce an effective offline training scheme to learn the dynamic rigidity prior by optimizing the convergence of the rigid pose optimization to the ground-truth poses in the training data. Our real-time face tracking system is an optimization framework that alternates between rigid pose optimization and expression optimization. To ensure tracking accuracy, we combine both robust, drift-free facial landmarks and dense optical flow into the optimization objectives. We evaluate our system extensively against state-of-the-art monocular face tracking systems and achieve significant improvement in tracking accuracy on the high-quality face tracking benchmark. Our system can improve facial-performance-based applications such as facial animation retargeting and virtual face makeup with accurate expression and stable pose. We further validate the dynamic rigidity prior by comparing it against other variants on the tracking accuracy.

Similar Papers
  • Conference Article
  • Citations1

The Study and Implementation of Face Recognition and Tracking System

  • Dec 01, 2009
  • Kai Chen +1
  • Research Article
  • Citations3

A real-time skin color based human face tracking system using an evolutionary search strategy

  • Sep 01, 2013
  • Ching-Yi Chen +2
  • Conference Article
  • Citations3

Research and implementation of real-time face detection, tracking and protection

  • Nov 02, 2003
  • De-Jiao Niu +2
  • Research Article

Three‐stage model for robust real‐time face tracking

  • Jan 01, 2007
  • International Journal of Imaging Systems and Technology
  • Jun-Hyeong Do +1
  • PDF
  • Research Article
  • Citations32

Real-Time Bottom Tracking Using Side Scan Sonar Data Through One-Dimensional Convolutional Neural Networks

  • Dec 20, 2019
  • Remote Sensing
  • Jun Yan +2
  • Book Chapter
  • Citations5

Study on Real-Time Face Recognition and Tracking for Criminal Revealing

  • Jan 01, 2020
  • A Krishna Chaitanya +2
  • Research Article
  • Citations5

Fuzzy system-based real-time face tracking in a multi-subject environment with a pan-tilt-zoom camera

  • Dec 17, 2009
  • Expert Systems With Applications
  • Chia-Feng Juang +1
  • Conference Article
  • Citations26

Face recognition and tracking for human-robot interaction*

  • Dec 01, 2004
  • Kai-Tai Song +1
  • Conference Article
  • Citations1

Driver face tracking using semantics-based feature of eyes on single FPGA

  • Jun 19, 2017
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Ying-Hao Yu +3
  • Conference Article
  • Citations1

Face Tracking Using Unscented Kalman Filter

  • Jan 01, 2020
  • Thathupara Subramanyan Kavya +4
  • Conference Article
  • Citations3

Automated face tracking with self correction capability

  • Oct 01, 2011
  • Mehrdad Sabet +3
  • PDF
  • Research Article
  • Citations10

Particle Filter Vehicles Tracking by Fusing Multiple Features

  • Jan 01, 2019
  • IEEE Access
  • Yu Wang +7
  • Conference Article
  • Citations3

Mobile Real-time Facial Expression Tracking with the Assistant of Public AI-as-a-Service

  • Dec 01, 2020
  • Xuncheng Liu +3
  • Conference Article
  • Citations3

Multi-Cue Adaptive Correlation Filters for Visual Tracking

  • Dec 01, 2016
  • Chang Liu +3
  • Book Chapter
  • Citations6

Development of Accurate Face Recognition Process Flow for Authentication

  • Nov 17, 2017
  • Tripty Singh +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.