# A Differential Approach for Gaze Estimation

arXiv: https://arxiv.org/abs/1904.09459 · HTML: https://mlsanity.com/paper/1904.09459/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2019.

## Built on by (most cited first, 26 of 26)

- [Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark](https://mlsanity.com/paper/2104.12668/) (2021)
- [ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour](https://mlsanity.com/paper/2307.01630/) (2023)
- [Automatic Gaze Analysis: A Survey of Deep Learning based Approaches](https://mlsanity.com/paper/2108.05479/) (2021)
- [Weakly-Supervised Physically Unconstrained Gaze Estimation](https://mlsanity.com/paper/2105.09803/) (2021)
- [Contrastive Representation Learning for Gaze Estimation](https://mlsanity.com/paper/2210.13404/) (2022)
- [Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimation](https://mlsanity.com/paper/2404.05215/) (2024)
- [3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views](https://mlsanity.com/paper/2212.02997/) (2022)
- [Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels](https://mlsanity.com/paper/2502.20249/) (2025)
- [Test-Time Personalization with Meta Prompt for Gaze Estimation](https://mlsanity.com/paper/2401.01577/) (2024)
- [Towards Self-Supervised Gaze Estimation](https://mlsanity.com/paper/2203.10974/) (2022)
- [Interaction-aware Joint Attention Estimation Using People Attributes](https://mlsanity.com/paper/2308.05382/) (2023)
- [The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation](https://mlsanity.com/paper/2106.14183/) (2021)
- [Appearance Debiased Gaze Estimation via Stochastic Subject-Wise Adversarial Learning](https://mlsanity.com/paper/2401.13865/) (2024)
- [Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation](https://mlsanity.com/paper/2412.15601/) (2024)
- [Merging Multiple Datasets for Improved Appearance-Based Gaze Estimation](https://mlsanity.com/paper/2409.00912/) (2024)
- [Multistream Gaze Estimation with Anatomical Eye Region Isolation by Synthetic to Real Transfer Learning](https://mlsanity.com/paper/2206.09256/) (2022)
- [Gaze Estimation Approach Using Deep Differential Residual Network](https://mlsanity.com/paper/2208.04298/) (2022)
- [GazeGen: Gaze-Driven User Interaction for Visual Content Generation](https://mlsanity.com/paper/2411.04335/) (2024)
- [QualitEye: Public and Privacy-preserving Gaze Data Quality Verification](https://mlsanity.com/paper/2506.05908/) (2025)
- [Investigating Bias and Fairness in Appearance-based Gaze Estimation](https://mlsanity.com/paper/2604.10707/) (2026)
- [MAGE: A Multi-task Architecture for Gaze Estimation with an Efficient Calibration Module](https://mlsanity.com/paper/2505.16384/) (2025)
- [Do you see what I see? An Ambiguous Optical Illusion Dataset exposing limitations of Explainable AI](https://mlsanity.com/paper/2505.21589/) (2025)
- [Pose-Robust Calibration Strategy for Point-of-Gaze Estimation on Mobile Phones](https://mlsanity.com/paper/2508.10268/) (2025)
- [GazeMoE: Perception of Gaze Target with Mixture-of-Experts](https://mlsanity.com/paper/2603.06256/) (2026)
- [Polarization-Based Eye Tracking with Personalized Siamese Architectures](https://mlsanity.com/paper/2603.25889/) (2026)
- [Real-time Appearance-based Gaze Estimation for Open Domains](https://mlsanity.com/paper/2603.26945/) (2026)

## Abstract (arXiv)

Non-invasive gaze estimation methods usually regress gaze directions directly from a single face or eye image. However, due to important variabilities in eye shapes and inner eye structures amongst individuals, universal models obtain limited accuracies and their output usually exhibit high variance as well as biases which are subject dependent. Therefore, increasing accuracy is usually done through calibration, allowing gaze predictions for a subject to be mapped to his/her actual gaze. In this paper, we introduce a novel image differential method for gaze estimation. We propose to directly train a differential convolutional neural network to predict the gaze differences between two eye input images of the same subject. Then, given a set of subject specific calibration images, we can use the inferred differences to predict the gaze direction of a novel eye sample. The assumption is that by allowing the comparison between two eye images, annoyance factors (alignment, eyelid closing, illumination perturbations) which usually plague single image prediction methods can be much reduced, allowing better prediction altogether. Experiments on 3 public datasets validate our approach which constantly outperforms state-of-the-art methods even when using only one calibration sample or when the latter methods are followed by subject specific gaze adaptation.