Search Results for author: Jiawei Qin

Found 4 papers, 2 papers with code

Angle Range and Identity Similarity Enhanced Gaze and Head Redirection based on Synthetic data

no code implementations11 Sep 2023 Jiawei Qin, Xueting Wang

In this paper, we propose a method for improving the angular accuracy and photo-reality of gaze and head redirection in full-face images.

3D Face Reconstruction Data Augmentation

Domain-Adaptive Full-Face Gaze Estimation via Novel-View-Synthesis and Feature Disentanglement

no code implementations25 May 2023 Jiawei Qin, Takuru Shimoyama, Xucong Zhang, Yusuke Sugano

To bridge the inevitable gap between synthetic and real images, we further propose an unsupervised domain adaptation method suitable for synthetic full-face data.

3D Reconstruction Disentanglement +3

Rotation-Constrained Cross-View Feature Fusion for Multi-View Appearance-based Gaze Estimation

1 code implementation22 May 2023 Yoichiro Hisadome, Tianyi Wu, Jiawei Qin, Yusuke Sugano

This work proposes a generalizable multi-view gaze estimation task and a cross-view feature fusion method to address this issue.

Domain Generalization Gaze Estimation

Learning-by-Novel-View-Synthesis for Full-Face Appearance-Based 3D Gaze Estimation

1 code implementation20 Jan 2022 Jiawei Qin, Takuru Shimoyama, Yusuke Sugano

Despite recent advances in appearance-based gaze estimation techniques, the need for training data that covers the target head pose and gaze distribution remains a crucial challenge for practical deployment.

3D Face Reconstruction Data Augmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.