Learning an appearance-based gaze estimator from one million synthesised images

By Erroll Wood, Tadas Baltrusaitis, Louis-philippe Morency, Peter Robinson, Andreas Bulling. 2016

370 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Learning from Simulated and Unsupervised Images through Adversarial Training (2016, methodology): “Example output of SimGAN for the UnityEyes gaze estimation dataset [43].”
ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation (2020, methodology): “Therefore, these methods had to revert to the synthetic data from UnityEye [37] or the relatively small Columbia datasets [31].”
Fake it till you make it: face analysis in the wild using synthetic data alone (2021, methodology): “[69] rendered an eye region 3DMM for gaze estimation.”
Synthetic Data for Deep Learning (2019, methodology): “The structure of HGSM is based on anatomical studies, and its parameters are learned from the UnityEyes dataset [641].”
GazeDirector: Fully Articulated Eye Gaze Redirection in Video (2017, methodology): “We use procedural animation to pose the eyelids in the facial mesh by rotational ammount θ lid [41].”
OpenFace 2.0: Facial Behavior Analysis Toolkit (2018, methodology): “[79], to EyeTab geometry based model [71] and a kNN approach based on the UnityEyes dataset [69].”
It’s Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation (2016, background): “Consequently, recent years have seen an increasing number of gaze estimation datasets collected in everyday settings [9, 19, 24], including some at large scale [13, 36], or consisting of synthetic data [25, 32, 33].”
RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments (2018, methodology): “X Frontal SynthesEyes [56] RGB Synthesized eye patches Gaze vector 11,382 Varying X X All UnityEyes [55] RGB Synthesized eye patches Gaze vector 1,000,000 Varying X X All UT Multi-view [53] RGB Eye area + eye patches Gaze vector 1,152,000 60cm X X All Gaze Capture [28] RGB Face + eye patches 2D pos ”
MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation (2017, background): “Their latest model is fully morphable [56] and can synthesise large numbers of images in a few hours on commodity hardware [7].”
Controllable Continuous Gaze Redirection (2020, methodology): “, SynthesEyes [37] and UnityEyes [34], covers the full space of gaze direction but methods trained on them are not as photo-realistic as those trained on high-quality real images.”