# Hidden Footprints: Learning Contextual Walkability from 3D Human Trails

arXiv: https://arxiv.org/abs/2008.08701 · HTML: https://mlsanity.com/paper/2008.08701/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2020.

## Built on by (most cited first, 4 of 4)

- [Human Hands as Probes for Interactive Object Understanding](https://mlsanity.com/paper/2112.09120/) (2021)
- [Common Inpainted Objects In-N-Out of Context](https://mlsanity.com/paper/2506.00721/) (2025)
- [MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection](https://mlsanity.com/paper/2504.06801/) (2025)
- [Animating Street View](https://mlsanity.com/paper/2310.08534/) (2023)

## Abstract (arXiv)

Predicting where people can walk in a scene is important for many tasks, including autonomous driving systems and human behavior analysis. Yet learning a computational model for this purpose is challenging due to semantic ambiguity and a lack of labeled data: current datasets only tell you where people are, not where they could be. We tackle this problem by leveraging information from existing datasets, without additional labeling. We first augment the set of valid, labeled walkable regions by propagating person observations between images, utilizing 3D information to create what we call hidden footprints. However, this augmented data is still sparse. We devise a training strategy designed for such sparse labels, combining a class-balanced classification loss with a contextual adversarial loss. Using this strategy, we demonstrate a model that learns to predict a walkability map from a single image. We evaluate our model on the Waymo and Cityscapes datasets, demonstrating superior performance compared to baselines and state-of-the-art models.