# NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation

arXiv: https://arxiv.org/abs/2610.19330 · HTML: https://mlsanity.com/paper/2610.19330/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Self-improving MLLMs and synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Context Encoding for Semantic Segmentation](https://mlsanity.com/paper/1803.08904/) (2018)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [Robotic Guide Dog: Leading a Human with Leash-Guided Hybrid Physical Interaction](https://mlsanity.com/paper/2103.14300/) (2021)
- [GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance](https://mlsanity.com/paper/2503.12844/) (2025)
- [Towards Robotic Companions: Understanding Handler-Guide Dog Interactions for Informed Guide Dog Robot Design](https://mlsanity.com/paper/2402.06790/) (2024)
- [StreetNav: Leveraging Street Cameras to Support Precise Outdoor Navigation for Blind Pedestrians](https://mlsanity.com/paper/2310.00491/) (2023)
- [Identifying Crucial Objects in Blind and Low-Vision Individuals' Navigation](https://mlsanity.com/paper/2408.13175/) (2024)
- [Space-Aware Instruction Tuning: Dataset and Benchmark for Guide Dog Robots Assisting the Visually Impaired](https://mlsanity.com/paper/2502.07183/) (2025)
- [A Dataset for Crucial Object Recognition in Blind and Low-Vision Individuals' Navigation](https://mlsanity.com/paper/2407.16777/) (2024)
- [GuideNav: User-Informed Development of a Vision-Only Robotic Navigation Assistant For Blind Travelers](https://mlsanity.com/paper/2512.06147/) (2025)
- [Understanding Expectations for a Robotic Guide Dog for Visually Impaired People](https://mlsanity.com/paper/2501.04594/) (2025)
- [GuideTWSI: A Diverse Tactile Walking Surface Indicator Dataset from Synthetic and Real-World Images for Blind and Low-Vision Navigation](https://mlsanity.com/paper/2603.07060/) (2026)
- [Human-Centered Development of Guide Dog Robots: Quiet and Stable Locomotion Control](https://mlsanity.com/paper/2505.11808/) (2025)

## Abstract (arXiv)

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.