# SANPO: A Scene Understanding, Accessibility and Human Navigation Dataset

arXiv: https://arxiv.org/abs/2309.12172 · HTML: https://mlsanity.com/paper/2309.12172/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 48 references that are in the map.
- First posted on arXiv 21 Sep 2023.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Associating Objects with Transformers for Video Object Segmentation](https://mlsanity.com/paper/2106.02638/) (2021)
- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation](https://mlsanity.com/paper/2204.00987/) (2022)
- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (2021)
- [Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation](https://mlsanity.com/paper/2203.15041/) (2022)
- [The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/1905.00737/) (2019)
- [ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2012.05258/) (2020)
- [MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?](https://mlsanity.com/paper/2108.09518/) (2021)
- [A*3D Dataset: Towards Autonomous Driving in Challenging Environments](https://mlsanity.com/paper/1909.07541/) (2019)
- [Toward Human-Like Social Robot Navigation: A Large-Scale, Multi-Modal, Social Human Navigation Dataset](https://mlsanity.com/paper/2303.14880/) (2023)
- [DeepLab2: A TensorFlow Library for Deep Labeling](https://mlsanity.com/paper/2106.09748/) (2021)
- [DOLPHINS: Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving](https://mlsanity.com/paper/2207.07609/) (2022)
- [Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances](https://mlsanity.com/paper/2303.10280/) (2023)

## Built on by (most cited first, 10 of 10)

- [EgoLife: Towards Egocentric Life Assistant](https://mlsanity.com/paper/2503.03803/) (2025)
- [mmWalk: Towards Multi-modal Multi-view Walking Assistance](https://mlsanity.com/paper/2510.11520/) (2025)
- [Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cooking](https://mlsanity.com/paper/2507.03330/) (2025)
- [Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model](https://mlsanity.com/paper/2510.11509/) (2025)
- [Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?](https://mlsanity.com/paper/2511.17792/) (2025)
- [WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation](https://mlsanity.com/paper/2603.10703/) (2026)
- [Synthetic data augmentation for robotic mobility aids to support blind and low vision people](https://mlsanity.com/paper/2409.11164/) (2024)
- [Uncertainty-Gated Region-Level Retrieval for Robust Semantic Segmentation](https://mlsanity.com/paper/2512.18082/) (2025)
- [Safety-oriented sidewalk and road segmentation for smartphone-based assistive navigation](https://mlsanity.com/paper/2607.21137/) (2026)
- [Can Vision-Language Models Analyze Human-Centered Video? Mapping Model Capabilities and Human-AI Collaborative Workflows](https://mlsanity.com/paper/2609.27327/) (2026)

## Abstract (arXiv)

Vision is essential for human navigation. The World Health Organization (WHO) estimates that 43.3 million people were blind in 2020, and this number is projected to reach 61 million by 2050. Modern scene understanding models could empower these people by assisting them with navigation, obstacle avoidance and visual recognition capabilities. The research community needs high quality datasets for both training and evaluation to build these systems. While datasets for autonomous vehicles are abundant, there is a critical gap in datasets tailored for outdoor human navigation. This gap poses a major obstacle to the development of computer vision based Assistive Technologies. To overcome this obstacle, we present SANPO, a large-scale egocentric video dataset designed for dense prediction in outdoor human navigation environments. SANPO contains 701 stereo videos of 30+ seconds captured in diverse real-world outdoor environments across four geographic locations in the USA. Every frame has a high resolution depth map and 112K frames were annotated with temporally consistent dense video panoptic segmentation labels. The dataset also includes 1961 high-quality synthetic videos with pixel accurate depth and panoptic segmentation annotations to balance the noisy real world annotations with the high precision synthetic annotations. SANPO is already publicly available and is being used by mobile applications like Project Guideline to train mobile models that help low-vision users go running outdoors independently. To preserve anonymization during peer review, we will provide a link to our dataset upon acceptance. SANPO is available here: https://google-research-datasets.github.io/sanpo_dataset/