GuideDog: 一种用于视障和低视力者无障碍引导的现实世界单人视角多模态数据集
GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance
AI总结：
本文提出GuideDog数据集，包含22K图像描述对，用于提升视障者导航能力，通过人机协同标注提升数据质量，并展示深度感知评估基准，揭示当前多模态大语言模型在深度感知方面的挑战。
摘要：
对于受盲人和低视力影响的人群，安全和独立的导航仍是一个重大挑战，影响着全球22亿人。尽管多模态大语言模型（MLLM）为辅助导航提供了新机会，但进展受限于无障碍数据集的匮乏，因为创建这些数据集需要大量专家标注。为此，我们引入GuideDog，一个包含22K图像描述对（2K人工验证）的数据集，覆盖46个国家的现实世界行人场景。我们的人机标注流程将标注从生成转向验证，基于专家和研究确立的BLV指导标准，提高可扩展性的同时保持质量。我们还提出了GuideDogQA，一个包含818个样本的基准，评估物体识别和深度感知。实验表明，当前MLLM在深度感知和遵循这些标准方面仍面临挑战。
英文摘要：
For people affected by blindness and low vision (BLV), safe and independent navigation remains a major challenge, impacting over 2.2 billion individuals worldwide. Although multimodal large language models (MLLMs) offer new opportunities for assistive navigation, progress has been limited by the scarcity of accessibility-aware datasets, because creating them requires labor-intensive expert annotation. To this end, we introduce GuideDog, a novel dataset containing 22K image-description pairs (2K human-verified) capturing real-world pedestrian scenes across 46 countries. Our human-AI pipeline shifts annotation from generation to verification, grounded in established BLV guidance standards from experts and research, improving scalability while maintaining quality. We also present GuideDogQA, an 818-sample benchmark evaluating object recognition and depth perception. Experiments reveal that depth perception and adherence to these standards remain challenging for current MLLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
