paper-with-me

홈 › Papers

LatentGaze: Cross-Domain Gaze Estimation through Gaze-Aware Analytic Latent Code Manipulation

2022-09-21 · Isack Lee, Jun-Seok Yun, Hee Hyeon Kim, Youngju Na, Seok Bong Yoo

Although recent gaze estimation methods lay great emphasis on attentively extracting gaze-relevant features from facial or eye images, how to define features that include gaze-relevant components has been ambiguous. This obscurity makes the model learn not only gaze-relevant features but also irrelevant ones. In particular, it is fatal for the cross-dataset performance. To overcome this challenging issue, we propose a gaze-aware analytic manipulation method, based on a data-driven approach with generative adversarial network inversion's disentanglement characteristics, to selectively utilize gaze-relevant features in a latent code. Furthermore, by utilizing GAN-based encoder-generator process, we shift the input image from the target domain to the source domain image, which a gaze estimator is sufficiently aware. In addition, we propose gaze distortion loss in the encoder that prevents the distortion of gaze information. The experimental results demonstrate that our method achieves state-of-the-art gaze estimation accuracy in a cross-domain gaze estimation tasks. This code is available at https://github.com/leeisack/LatentGaze/.

📄 PDF Abstract BibTeX arXiv:2209.10171

Code (1)

leeisack/latentgaze 공식 구현 pytorch

Tasks

DisentanglementGaze EstimationGenerative Adversarial Network

Similar Papers 제목 키워드 기반

UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training

2025-02-04 · Jiawei Qin, Xucong Zhang, Yusuke Sugano

Despite decades of research on data collection and model architectures, current gaze estimation models face significant challenges in generalizing across diverse data domains. While recent advances in self-supervised pre…

Gaze Estimation

LG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze Estimation

2024-11-13 · Pengwei Yin, Jingjing Wang, Guanzhong Zeng, Di Xie 외

The ability of gaze estimation models to generalize is often significantly hindered by various factors unrelated to gaze, especially when the training dataset is limited. Current strategies aim to address this challenge …

Domain GeneralizationGaze Estimationregression

PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation

2021-03-24 · Yihua Cheng, Yiwei Bao, Feng Lu

Gaze estimation methods learn eye gaze from facial features. However, among rich information in the facial image, real gaze-relevant features only correspond to subtle changes in eye region, while other gaze-irrelevant f…

Domain AdaptationDomain GeneralizationGaze Estimation

Jitter Does Matter: Adapting Gaze Estimation to New Domains

2022-10-05 · Ruicong Liu, Yiwei Bao, Mingjie Xu, Haofei Wang 외

Deep neural networks have demonstrated superior performance on appearance-based gaze estimation tasks. However, due to variations in person, illuminations, and background, performance degrades dramatically when applying …

Adversarial AttackContrastive LearningDomain AdaptationGaze Estimation

See Through the Noise: Improving Domain Generalization in Gaze Estimation

2026-04-17 · Yanming Peng, Shijing Wang, Yaping Huang, Yi Tian arxiv

Generalizable gaze estimation methods have garnered increasing attention due to their critical importance in real-world applications and have achieved significant progress. However, they often overlook the effect of labe…

Domain GeneralizationGaze Estimation