FocusAdapt: Context-aware Adaptive Focus Assistance in Diminished Reality
2026-08-31 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors created a system called FocusAdapt that helps people focus on important things by making distracting objects less visible. Instead of removing everything that seems irrelevant, their system figures out which objects actually distract a person by looking at where they are looking and what the objects mean. This way, it keeps useful background information while reducing visual clutter. Their approach can help people stay focused during step-by-step tasks.
Diminished RealityVisual SaliencySemantic RelevanceGaze BehaviorContext AwarenessVisual ClutterDistraction PredictionProcedural Tasks
Authors
Tianyu Zhang, Shutong Wu, Jiankun Yang, Zhen Bai, Yukang Yan
Abstract
Diminished Reality (DR) can reduce visual clutter by removing irrelevant objects. However, removing all task-irrelevant objects may eliminate useful contextual information and reduce situational awareness. We present FocusAdapt, a context-aware DR system that predicts object-level distraction by integrating visual saliency, semantic relevance, and gaze behavior. Based on findings from a formative study, FocusAdapt selectively diminishes highly distracting objects while preserving useful context, enabling adaptive focus assistance during procedural tasks.