# DMAGaze: Gaze Estimation Based on Feature Disentanglement and Multi-Scale Attention

arXiv: https://arxiv.org/abs/2504.11160 · HTML: https://mlsanity.com/paper/2504.11160/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Gaze360: Physically Unconstrained Gaze Estimation in the Wild](https://mlsanity.com/paper/1910.10088/) (2019)
- [Eye Tracking for Everyone](https://mlsanity.com/paper/1606.05814/) (2016)
- [Appearance-Based Gaze Estimation in the Wild](https://mlsanity.com/paper/1504.02863/) (2015)
- [It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1611.08860/) (2016)
- [Agent Attention: On the Integration of Softmax and Linear Attention](https://mlsanity.com/paper/2312.08874/) (2023)
- [Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark](https://mlsanity.com/paper/2104.12668/) (2021)
- [Deep Visual Attention Prediction](https://mlsanity.com/paper/1705.02544/) (2017)
- [Gaze Estimation using Transformer](https://mlsanity.com/paper/2105.14424/) (2021)
- [A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation](https://mlsanity.com/paper/2001.00187/) (2020)
- [L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments](https://mlsanity.com/paper/2203.03339/) (2022)
- [PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation](https://mlsanity.com/paper/2103.13173/) (2021)
- [Appearance-Based Gaze Estimation Using Dilated-Convolutions](https://mlsanity.com/paper/1903.07296/) (2019)
- [Unsupervised Representation Learning for Gaze Estimation](https://mlsanity.com/paper/1911.06939/) (2019)
- [Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions](https://mlsanity.com/paper/2112.05561/) (2021)
- [CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model](https://mlsanity.com/paper/2403.05124/) (2024)
- [A Review of Driver Gaze Estimation and Application in Gaze Behavior Understanding](https://mlsanity.com/paper/2307.01470/) (2023)
- [SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention](https://mlsanity.com/paper/2407.05128/) (2024)
- [CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild](https://mlsanity.com/paper/2402.08316/) (2024)
- [INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization](https://mlsanity.com/paper/2309.04063/) (2023)
- [Merging Multiple Datasets for Improved Appearance-Based Gaze Estimation](https://mlsanity.com/paper/2409.00912/) (2024)
- [Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion](https://mlsanity.com/paper/2409.04766/) (2024)
- [EM-Net: Gaze Estimation with Expectation Maximization Algorithm](https://mlsanity.com/paper/2412.08074/) (2024)

## Abstract (arXiv)

Gaze estimation, which predicts gaze direction, commonly faces the challenge of interference from complex gaze-irrelevant information in face images. In this work, we propose DMAGaze, a novel gaze estimation framework that exploits information from facial images in three aspects: gaze-relevant global features (disentangled from facial image), local eye features (extracted from cropped eye patch), and head pose estimation features, to improve overall performance. Firstly, we design a new continuous mask-based Disentangler to accurately disentangle gaze-relevant and gaze-irrelevant information in facial images by achieving the dual-branch disentanglement goal through separately reconstructing the eye and non-eye regions. Furthermore, we introduce a new cascaded attention module named Multi-Scale Global Local Attention Module (MS-GLAM). Through a customized cascaded attention structure, it effectively focuses on global and local information at multiple scales, further enhancing the information from the Disentangler. Finally, the global gaze-relevant features disentangled by the upper face branch, combined with head pose and local eye features, are passed through the detection head for high-precision gaze estimation. Our proposed DMAGaze has been extensively validated on two mainstream public datasets, achieving state-of-the-art performance.