Exploring AR Label Placements in Visually Cluttered Scenarios

2025-06-30

AI Summary

In dense augmented reality (AR) scenes with visually cluttered, semantically homogeneous objects, conventional label placement degrades label readability and task efficiency. To address this, we propose three spatial-clustering–based label layout techniques that group labels of同类 objects according to their spatial distribution and semantic type within the user’s field of view (FoV), thereby enabling visual structuring. Our approach jointly incorporates FoV-aware constraints, semantic clustering, and geometric optimization—moving beyond the traditional one-label–one-object mapping paradigm. A user study demonstrates significant improvements: +28% in object identification accuracy, −31% reduction in response time for comparative tasks, and +22% increase in data summarization correctness. The proposed framework provides a scalable, perceptually grounded label layout paradigm for high-density AR visualization.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Search and Optimization: Distributed Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

We investigate methods for placing labels in AR environments that have visually cluttered scenes. As the number of items increases in a scene within the user' FOV, it is challenging to effectively place labels based on existing label placement guidelines. To address this issue, we implemented three label placement techniques for in-view objects for AR applications. We specifically target a scenario, where various items of different types are scattered within the user's field of view, and multiple items of the same type are situated close together. We evaluate three placement techniques for three target tasks. Our study shows that using a label to spatially group the same types of items is beneficial for identifying, comparing, and summarizing data.

Problem

• Methods for placing labels in cluttered AR scenes
• Challenges with existing label placement guidelines
• Evaluating techniques for grouping same-type items

Innovation

• AR label placement in cluttered scenes
• Spatial grouping for same-type items
• Three techniques for in-view objects