MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation
By Xucong Zhang, Yusuke Sugano, Mario Fritz, Andreas Bulling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
588 citations recorded by the source corpus.
Learning-based methods are believed to work well for unconstrained gaze estimation, i.e. gaze estimation from a monocular RGB camera without assumptions regarding user, environment, or camera. However, current gaze datasets were collected under laboratory conditions and methods were not evaluated across multiple datasets. Our work makes three contributions towards addressing these limitations. First, we present the MPIIGaze dataset, which contains 213,659 full face images and corresponding ground-truth gaze positions collected from 15 users during everyday laptop use over several months. An experience sampling approach ensured continuous gaze and head poses and realistic variation in eye appearance and illumination. To facilitate cross-dataset evaluations, 37,667 images were manually annotated with eye corners, mouth corners, and pupil centres. Second, we present an extensive evaluation of state-of-the-art gaze estimation methods on three current datasets, including MPIIGaze. We study key challenges including target gaze range, illumination conditions, and facial appearance variation. We show that image resolution and the use of both eyes affect gaze estimation performance, while head pose and pupil centre information are less informative. Finally, we propose GazeNet, the first deep appearance-based gaze estimation method. GazeNet improves on the state of the art by 22 percent (from a mean error of 13.9 degrees to 10.8 degrees) for the most challenging cross-dataset evaluation.
Subfields: Radiology, Nuclear Medicine and Imaging, Urban Studies, Human-Computer Interaction
View Paper: https://www.semanticscholar.org/paper/01be6c81374acf31bcbabfea7ef7471601fa8987
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Radiology, Nuclear Medicine and Imaging
- Antonio Torralba
- Petr Kellnhofer
- Wojciech Matusik
- Hadi Pouransari
- Yukun Zhu
- Bradley Green
- Oncel Tuzel
- Scott Niekum
In Urban Studies
In Human-Computer Interaction
- Ruohan Zhang
- Scott Niekum
- Akanksha Saran
- Dana H. Ballard
- Antonio Torralba
- Mary M. Hayhoe
- Sihang Guo
- Petr Kellnhofer
Citations in the corpus
- Gaze360: Physically Unconstrained Gaze Estimation in the Wild (2019, methodology): “Existing methods [12, 32] do not deal with these cases and typically assume that the subject is facing the camera.”
- Human Gaze Assisted Artificial Intelligence: A Review (2020, result): “…accuracy and are more robust to visual appearance variations [Zhang et al. , 2015; Wood et al. , 2015; Krafka et al. , 2016; Shrivastava et al. , 2017; Zhang et al. , 2017; Park et al. , 2018], compared to more traditional approaches like hand-crafted feature-based or model-based algorithms.”
- Boosting Image-based Mutual Gaze Detection using Pseudo 3D Gaze (2020, background): “(Zhang et al. 2017b) collected a 3D gaze estimation dataset from 15 users during their laptop usage over several months.”
- Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution (2020, methodology): “Our training setup matches the accuracies reported in the original works [67, 68].”