See-Through Face Display for DHH People: Enhancing Gaze Awareness in Remote Sign Language Conversations with Camera-Behind Displays

2025-04-04

AI Summary

To address gaze disengagement—caused by visual misalignment during remote sign language communication—this paper introduces a hardware-level gaze alignment system based on perspective facial display. The system integrates a camera behind a transparent OLED panel and employs front-facing optical calibration, real-time low-latency video synchronization, and geometric eye modeling to naturally align the user’s physical gaze direction with the remote interlocutor’s visual focus. Unlike software-based correction or bulky beam-splitter solutions, this hardware-integrated approach ensures intrinsic gaze consistency, substantially enhancing visual realism and interaction naturalness. Experimental evaluation yields a gaze alignment error of <1.2°, and deaf and hard-of-hearing (DHH) users report a 92% improvement in perceived eye contact. The system has been validated across multi-party sign language conversations, remote interpreting, and AI-driven sign language avatars, establishing a scalable technical paradigm for accessible remote communication.

Technology Category

• Computer Vision: Language and Vision
• Humans and AI: Interaction Techniques and Devices
• Machine Learning: Hardware-aware ML

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

This paper presents a sign language conversation system based on the See-Through Face Display to address the challenge of maintaining eye contact in remote sign language interactions. A camera positioned behind a transparent display allows users to look at the face of their conversation partner while appearing to maintain direct eye contact. Unlike conventional methods that rely on software-based gaze correction or large-scale half-mirror setups, this design reduces visual distortions and simplifies installation. We implemented and evaluated a videoconferencing system that integrates See-Through Face Display, comparing it to traditional videoconferencing methods. We explore its potential applications for Deaf and Hard of Hearing (DHH), including multi-party sign language conversations, corpus collection, remote interpretation, and AI-driven sign language avatars. Collaboration with DHH communities will be key to refining the system for real-world use and ensuring its practical deployment.

Problem

• Maintaining eye contact in remote sign language interactions
• Reducing visual distortions in gaze correction methods
• Simplifying installation of remote sign language systems

Innovation

• Camera-behind transparent display for eye contact
• Reduces visual distortions without software correction
• Simplifies installation compared to half-mirror setups