Large dataset and synthetic data help blind navigation object recognition
NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation
Computer Vision and Pattern RecognitionRobotics
Summary
Helping blind and low-vision people move safely requires recognizing important objects like buttons and handrails. The authors created NavAble, a big collection of real and computer-generated images focused on these accessibility features. Their method uses smart tools to gather and make many diverse images with detailed labels, which helps train AI to spot these objects well. Testing showed AI trained on NavAble could recognize these objects reliably, even in real robots helping with navigation. This work tackles the problem of not having enough data to teach AI to understand these critical items.
What this means in practice
- •For assistive technology developers: Improve device perception to reliably detect accessibility objects critical for blind navigation in real-world scenarios.
- •For robotics engineers: Enhance perception modules on mobility-assistive robots with diverse training data for better object recognition during navigation.
Authors
Hochul Hwang, Jahir Sadik Monon, Soowan Yang, Shiven Umeshbhai Patel, Anh Nhat Hong Nguyen, Kien Nguyen, Keshav Garg, Dylan Gage, Duretti Hordofaa, Anshu Anjna, Eshed Ohn-Bar, Donghyun Kim
Abstract
Reliable recognition of accessibility-critical objects (e.g., audible pedestrian signals, door-activation buttons, and handrails) is essential for assistive navigation technologies that support safe, independent mobility for blind and low-vision (BLV) users. Yet these categories are underrepresented in existing large-scale vision datasets, and the few datasets that include them suffer from limited class coverage, inconsistent annotations, and poor diversity. We introduce NavAble, a large-scale dataset spanning 11 accessibility-critical object classes, combining 41K curated open-source images with 8K newly collected, densely annotated real-world images. To extend scale and diversity, we develop a synthetic data generation pipeline that renders high-fidelity 3D assets across 37 environments under diverse styles and viewpoints, yielding 452K frames with rich ground-truth annotations from 565 assets. The pipeline minimizes manual effort by combining automated web image crawling, VLM-based filtering, SAM 3D-based asset generation, and convenient camera trajectory configuration, enabling large-scale data generation at a diversity unattainable through manual collection. Experiments show that fine-tuning existing segmentation models on the NavAble Dataset achieves reliable accessibility-object segmentation (>80% mIoU on our held-out test set). We also demonstrate the effectiveness of synthetic data augmentation, which yields up to +3.5 mIoU over real-world-only fine-tuning. Beyond benchmark evaluation, validation on egocentric data from two mobility-assistive robots demonstrates improved perception reliability in real-world navigation scenarios. Together, NavAble establishes a scalable foundation for BLV navigation perception, directly addressing the data scarcity and embodiment gaps. The dataset and pipeline are publicly available at https://huggingface.co/datasets/NavAble/NeurIPS_2026_BLV.