Real-time Appearance-based Gaze Estimation for Open Domains

• URL: http://arxiv.org/abs/2603.26945v1
• Date: Fri, 27 Mar 2026 19:33:18 GMT
• Title: Real-time Appearance-based Gaze Estimation for Open Domains
• Abstract summary: We propose a robust AGE framework that enhances generalization without requiring additional human-annotated data.<n>To mitigate the impact of anisotropic inter-dataset label deviation, we reformulate gaze regression as a multi-task learning problem.<n>Our MobileNet-based lightweight model generalization achieves performance competitive with the state-of-the-art (SOTA) UniGaze-H.
• Score: 15.195617974731766
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Appearance-based gaze estimation (AGE) has achieved remarkable performance in constrained settings, yet we reveal a significant generalization gap where existing AGE models often fail in practical, unconstrained scenarios, particularly those involving facial wearables and poor lighting conditions. We attribute this failure to two core factors: limited image diversity and inconsistent label fidelity across different datasets, especially along the pitch axis. To address these, we propose a robust AGE framework that enhances generalization without requiring additional human-annotated data. First, we expand the image manifold via an ensemble of augmentation techniques, including synthesis of eyeglasses, masks, and varied lighting. Second, to mitigate the impact of anisotropic inter-dataset label deviation, we reformulate gaze regression as a multi-task learning problem, incorporating multi-view supervised contrastive (SupCon) learning, discretized label classification, and eye-region segmentation as auxiliary objectives. To rigorously validate our approach, we curate new benchmark datasets designed to evaluate gaze robustness under challenging conditions, a dimension largely overlooked by existing evaluation protocols. Our MobileNet-based lightweight model achieves generalization performance competitive with the state-of-the-art (SOTA) UniGaze-H, while utilizing less than 1\% of its parameters, enabling high-fidelity, real-time gaze tracking on mobile devices.

Related papers

• Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework [12.197772777447405]
  Image enhancement and restoration have become standard back-end operations on short-video and social media platforms to boost visual experience.<n>Existing IQA methods fail to capture the specific, localized anomalies caused by enhancement algorithms in real-world scenarios.<n>We formally define a new task-quality Anomaly Perception for image Enhancement (UEAP)<n>We contribute the first UEAP benchmark dataset, named UEAP-4k, curated from the real business scenarios.
  arXiv  Detail & Related papers  (2026-09-02T12:37:56Z)
• OmniGaze: Reward-inspired Generalizable Gaze Estimation In The Wild [104.57404324262556]
  Current 3D gaze estimation methods struggle to generalize across diverse data domains.<n>We present OmniGaze, a semi-supervised framework for 3D gaze estimation.<n>We show that OmniGaze achieves state-of-the-art performance on five datasets.
  arXiv  Detail & Related papers  (2025-10-15T15:19:52Z)
• Unsupervised Dynamic Feature Selection for Robust Latent Spaces in Vision Tasks [5.167904179040144]
  This paper presents a novel approach for enhancing latent representations using unsupervised Dynamic Feature Selection (DFS)<n>For each instance, the proposed method identifies and removes misleading or redundant information in images, ensuring that only the most relevant features contribute to the latent space.<n>Experiments conducted on image datasets demonstrate that models equipped with unsupervised DFS achieve significant improvements in generalization performance across various tasks.
  arXiv  Detail & Related papers  (2025-10-02T07:46:59Z)
• Saccadic Vision for Fine-Grained Visual Classification [10.681604440788854]
  Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features.<n>Existing part-based methods rely on complex localization networks that learn mappings from pixel to sample space.<n>We propose a two-stage process that first extracts peripheral features and generates a sample map.<n>We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations.
  arXiv  Detail & Related papers  (2025-09-19T07:03:37Z)
• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• CRIA: A Cross-View Interaction and Instance-Adapted Pre-training Framework for Generalizable EEG Representations [52.251569042852815]
  CRIA is an adaptive framework that utilizes variable-length and variable-channel coding to achieve a unified representation of EEG data across different datasets.<n>The model employs a cross-attention mechanism to fuse temporal, spectral, and spatial features effectively.<n> Experimental results on the Temple University EEG corpus and the CHB-MIT dataset show that CRIA outperforms existing methods with the same pre-training conditions.
  arXiv  Detail & Related papers  (2025-06-19T06:31:08Z)
• UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training [12.680014448486242]
  We propose UniGaze, leveraging large-scale in-the-wild facial datasets for gaze estimation through self-supervised pre-training.<n>Our experiments reveal that self-supervised approaches designed for semantic tasks fail when applied to gaze estimation.<n>We demonstrate that UniGaze significantly improves generalization across multiple data domains while minimizing reliance on costly labeled data.
  arXiv  Detail & Related papers  (2025-02-04T13:24:23Z)
• Improving Domain Generalization on Gaze Estimation via Branch-out Auxiliary Regularization [3.3539987257923247]
  Branch-out Auxiliary Regularization (BAR) is designed to boost gaze estimation's generalization capabilities without requiring direct access to target domain data. Bar integrates two auxiliary consistency regularization branches: one that uses augmented samples to counteract environmental variations, and another that aligns gaze directions with positive source domain samples to encourage the learning of consistent gaze features.
  arXiv  Detail & Related papers  (2024-05-02T16:26:37Z)
• Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Models [58.46926334842161]
  This work illuminates the fundamental reasons for such misalignment, pinpointing issues related to low attention activation scores and mask overlaps. We propose two novel objectives, the Separate loss and the Enhance loss, that reduce object mask overlaps and maximize attention scores. Our method diverges from conventional test-time-adaptation techniques, focusing on finetuning critical parameters, which enhances scalability and generalizability.
  arXiv  Detail & Related papers  (2023-12-10T22:07:42Z)
• Semi-supervised Contrastive Regression for Estimation of Eye Gaze [0.609170287691728]
  This paper develops a semi-supervised contrastive learning framework for estimation of gaze direction. With a small labeled gaze dataset, the framework is able to find a generalized solution even for unseen face images. Our contrastive regression framework shows good performance in comparison to several state of the art contrastive learning techniques used for gaze estimation.
  arXiv  Detail & Related papers  (2023-08-05T04:11:38Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis [76.46004354572956]
  We introduce an unsupervised domain adaptation approach for person re-identification. Experimental results show that the proposed ktCUDA and SHRED approach achieves an average improvement of +5.7 mAP in re-identification performance.
  arXiv  Detail & Related papers  (2020-01-14T17:43:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.