# L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments

arXiv: https://arxiv.org/abs/2203.03339 · HTML: https://mlsanity.com/paper/2203.03339/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 7 Mar 2022.

## Builds on (most cited first, 8 of 8)

- [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)
- [ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation](https://mlsanity.com/paper/2007.15837/) (2020)
- [It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1611.08860/) (2016)
- [MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1711.09017/) (2017)
- [Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark](https://mlsanity.com/paper/2104.12668/) (2021)
- [A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation](https://mlsanity.com/paper/2001.00187/) (2020)
- [Appearance-Based Gaze Estimation Using Dilated-Convolutions](https://mlsanity.com/paper/1903.07296/) (2019)

## Built on by (most cited first, 30 of 65)

- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time](https://mlsanity.com/paper/2404.10667/) (2024)
- [Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis](https://mlsanity.com/paper/2211.14506/) (2022)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors](https://mlsanity.com/paper/2212.04248/) (2022)
- [CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models](https://mlsanity.com/paper/2412.12093/) (2024)
- [MegActor: Harness the Power of Raw Video for Vivid Portrait Animation](https://mlsanity.com/paper/2405.20851/) (2024)
- [Face Anonymization Made Simple](https://mlsanity.com/paper/2411.00762/) (2024)
- [MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars](https://mlsanity.com/paper/2510.12785/) (2025)
- [End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context](https://mlsanity.com/paper/2310.18131/) (2023)
- [An End-to-End Review of Gaze Estimation and its Interactive Applications on Handheld Mobile Devices](https://mlsanity.com/paper/2307.00122/) (2023)
- [Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimation](https://mlsanity.com/paper/2404.05215/) (2024)
- [Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels](https://mlsanity.com/paper/2502.20249/) (2025)
- [Disguise without Disruption: Utility-Preserving Face De-Identification](https://mlsanity.com/paper/2303.13269/) (2023)
- [UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training](https://mlsanity.com/paper/2502.02307/) (2025)
- [CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild](https://mlsanity.com/paper/2402.08316/) (2024)
- [A First Step in Using Machine Learning Methods to Enhance Interaction Analysis for Embodied Learning Environments](https://mlsanity.com/paper/2405.06203/) (2024)
- [One Eye is All You Need: Lightweight Ensembles for Gaze Estimation with Single Encoders](https://mlsanity.com/paper/2211.11936/) (2022)
- [Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method](https://mlsanity.com/paper/2403.16169/) (2024)
- [OpenFace 3.0: A Lightweight Multitask System for Comprehensive Facial Behavior Analysis](https://mlsanity.com/paper/2506.02891/) (2025)
- [NullFace: Training-Free Localized Face Anonymization](https://mlsanity.com/paper/2503.08478/) (2025)
- [Introducing Explicit Gaze Constraints to Face Swapping](https://mlsanity.com/paper/2305.16138/) (2023)
- [GazeForensics: DeepFake Detection via Gaze-guided Spatial Inconsistency Learning](https://mlsanity.com/paper/2311.07075/) (2023)
- [Learning Gaze-aware Compositional GAN](https://mlsanity.com/paper/2405.20643/) (2024)
- [Stable Video-Driven Portraits](https://mlsanity.com/paper/2509.17476/) (2025)
- [Now You See Me, Now You Don't: A Unified Framework for Expression Consistent Anonymization in Talking Head Videos](https://mlsanity.com/paper/2601.11635/) (2026)
- [SLYKLatent: A Learning Framework for Gaze Estimation Using Deep Facial Feature Learning](https://mlsanity.com/paper/2402.01555/) (2024)
- [Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms](https://mlsanity.com/paper/2402.03188/) (2024)
- [3D Gaze Tracking for Studying Collaborative Interactions in Mixed-Reality Environments](https://mlsanity.com/paper/2406.11003/) (2024)
- [EraW-Net: Enhance-Refine-Align W-Net for Scene-Associated Driver Attention Estimation](https://mlsanity.com/paper/2408.08570/) (2024)

## Abstract (arXiv)

Human gaze is a crucial cue used in various applications such as human-robot interaction and virtual reality. Recently, convolution neural network (CNN) approaches have made notable progress in predicting gaze direction. However, estimating gaze in-the-wild is still a challenging problem due to the uniqueness of eye appearance, lightning conditions, and the diversity of head pose and gaze directions. In this paper, we propose a robust CNN-based model for predicting gaze in unconstrained settings. We propose to regress each gaze angle separately to improve the per-angel prediction accuracy, which will enhance the overall gaze performance. In addition, we use two identical losses, one for each angle, to improve network learning and increase its generalization. We evaluate our model with two popular datasets collected with unconstrained settings. Our proposed model achieves state-of-the-art accuracy of 3.92deg and 10.41deg on MPIIGaze and Gaze360 datasets, respectively. We make our code open source at https://github.com/Ahmednull/L2CS-Net.