paper-with-me

Papers

360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales

2020-09-15 · Ashesh, Chu-Song Chen, Hsuan-Tien Lin

Gaze estimation involves predicting where the person is looking at within an image or video. Technically, the gaze information can be inferred from two different magnification levels: face orientation and eye orientation. The inference is not always feasible for gaze estimation in the wild, given the lack of clear eye patches in conditions like extreme left/right gazes or occlusions. In this work, we design a model that mimics humans' ability to estimate the gaze by aggregating from focused looks, each at a different magnification level of the face area. The model avoids the need to extract clear eye patches and at the same time addresses another important issue of face-scale variation for gaze estimation in the wild. We further extend the model to handle the challenging task of 360-degree gaze estimation by encoding the backward gazes in the polar representation along with a robust averaging scheme. Experiment results on the ETH-XGaze dataset, which does not contain scale-varying faces, demonstrate the model's effectiveness to assimilate information from multiple scales. For other benchmark datasets with many scale-varying faces (Gaze360 and RT-GENE), the proposed model achieves state-of-the-art performance for gaze estimation when using either images or videos. Our code and pretrained models can be accessed at https://github.com/ashesh-0/MultiZoomGaze.

📄 PDF Abstract BibTeX arXiv:2009.06924

Code (1)

ashesh-0/multizoomgaze 공식 구현 pytorch

Tasks

Gaze Estimation

Similar Papers 제목 키워드 기반

Towards Precision in Appearance-based Gaze Estimation in the Wild

2023-02-05 · Murthy L. R. D., Abhishek Mukhopadhyay, Shambhavi Aggarwal, Ketan Anand 외

Appearance-based gaze estimation systems have shown great progress recently, yet the performance of these techniques depend on the datasets used for training. Most of the existing gaze estimation datasets setup in intera…

Gaze Estimation

Appearance-Based Gaze Estimation in the Wild

2015-04-11 · CVPR 2015 6 · Xucong Zhang, Yusuke Sugano, Mario Fritz, Andreas Bulling

Appearance-based gaze estimation is believed to work well in real-world settings, but existing datasets have been collected under controlled laboratory conditions and methods have been not evaluated across multiple datas…

Gaze Estimation

GazeOnce: Real-Time Multi-Person Gaze Estimation

2022-04-20 · CVPR 2022 1 · Mingfang Zhang, Yunfei Liu, Feng Lu

Appearance-based gaze estimation aims to predict the 3D eye gaze direction from a single image. While recent deep learning-based approaches have demonstrated excellent performance, they usually assume one calibrated face…

Gaze Estimation

CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild

2024-02-13 · Andy Cătrună, Adrian Cosma, Emilian Rădoi

Gaze estimation, the task of predicting where an individual is looking, is a critical task with direct applications in areas such as human-computer interaction and virtual reality. Estimating the direction of looking in …

Gaze EstimationGaze Prediction

ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild

2022-08-23 · Lumin Xu, Sheng Jin, Wentao Liu, Chen Qian 외

This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We propose a single-network approach, termed…

2D Human Pose EstimationNeural Architecture SearchPose Estimation