LatentGaze: Cross-Domain Gaze Estimation through Gaze-Aware Analytic Latent Code Manipulation
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/.
Code (1)
Tasks
DisentanglementGaze EstimationGenerative Adversarial NetworkSimilar Papers 제목 키워드 기반
UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training
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 EstimationLG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze Estimation
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 EstimationregressionPureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation
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 EstimationJitter Does Matter: Adapting Gaze Estimation to New Domains
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 EstimationSee Through the Noise: Improving Domain Generalization in Gaze Estimation
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