Zhengyang Wu

Zhengyang Wu, Srivignesh Rajendran, Tarrence van As et al.

With the emergence of Virtual and Mixed Reality (XR) devices, eye tracking has received significant attention in the computer vision community. Eye gaze estimation is a crucial component in XR -- enabling energy efficient rendering, multi-focal displays, and effective interaction with content. In head-mounted XR devices, the eyes are imaged off-axis to avoid blocking the field of view. This leads to increased challenges in inferring eye related quantities and simultaneously provides an opportunity to develop accurate and robust learning based approaches. To this end, we present MagicEyes, the first large scale eye dataset collected using real MR devices with comprehensive ground truth labeling. MagicEyes includes $587$ subjects with $80,000$ images of human-labeled ground truth and over $800,000$ images with gaze target labels. We evaluate several state-of-the-art methods on MagicEyes and also propose a new multi-task EyeNet model designed for detecting the cornea, glints and pupil along with eye segmentation in a single forward pass.

Zhengyang Wu, Srivignesh Rajendran, Tarrence van As et al.

Eye gaze estimation and simultaneous semantic understanding of a user through eye images is a crucial component in Virtual and Mixed Reality; enabling energy efficient rendering, multi-focal displays and effective interaction with 3D content. In head-mounted VR/MR devices the eyes are imaged off-axis to avoid blocking the user's gaze, this view-point makes drawing eye related inferences very challenging. In this work, we present EyeNet, the first single deep neural network which solves multiple heterogeneous tasks related to eye gaze estimation and semantic user understanding for an off-axis camera setting. The tasks include eye segmentation, blink detection, emotive expression classification, IR LED glints detection, pupil and cornea center estimation. To train EyeNet end-to-end we employ both hand labelled supervision and model based supervision. We benchmark all tasks on MagicEyes, a large and new dataset of 587 subjects with varying morphology, gender, skin-color, make-up and imaging conditions.

Zhengyang Wu, Mohit Bansal, Matthew R. Walter

In order for robots to operate effectively in homes and workplaces, they must be able to manipulate the articulated objects common within environments built for and by humans. Previous work learns kinematic models that prescribe this manipulation from visual demonstrations. Lingual signals, such as natural language descriptions and instructions, offer a complementary means of conveying knowledge of such manipulation models and are suitable to a wide range of interactions (e.g., remote manipulation). In this paper, we present a multimodal learning framework that incorporates both visual and lingual information to estimate the structure and parameters that define kinematic models of articulated objects. The visual signal takes the form of an RGB-D image stream that opportunistically captures object motion in an unprepared scene. Accompanying natural language descriptions of the motion constitute the lingual signal. We present a probabilistic language model that uses word embeddings to associate lingual verbs with their corresponding kinematic structures. By exploiting the complementary nature of the visual and lingual input, our method infers correct kinematic structures for various multiple-part objects on which the previous state-of-the-art, visual-only system fails. We evaluate our multimodal learning framework on a dataset comprised of a variety of household objects, and demonstrate a 36% improvement in model accuracy over the vision-only baseline.