# Toward Robust Single-Photon Perception for Robots: A Condition-Aware Active Learning Approach

arXiv: https://arxiv.org/abs/2505.04376 · HTML: https://mlsanity.com/paper/2505.04376/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 13 of 13)

- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Virtual KITTI 2](https://mlsanity.com/paper/2001.10773/) (2020)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [The Importance of Metric Learning for Robotic Vision: Open Set Recognition and Active Learning](https://mlsanity.com/paper/1902.10363/) (2019)
- [Single-photon imaging over 200 km](https://mlsanity.com/paper/2103.05860/) (2021)
- [Enhancing Autonomous Navigation by Imaging Hidden Objects using Single-Photon LiDAR](https://mlsanity.com/paper/2410.03555/) (2024)
- [Discwise Active Learning for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2309.13276/) (2023)
- [Time-Resolved MNIST Dataset for Single-Photon Recognition](https://mlsanity.com/paper/2410.16744/) (2024)
- [Robust and Efficient Depth-based Obstacle Avoidance for Autonomous Miniaturized UAVs](https://mlsanity.com/paper/2208.12624/) (2022)

## Abstract (arXiv)

LiDAR-based perception plays a fundamental role in modern robotic systems for environment understanding and navigation. Single-photon LiDAR (SPL) extends conventional LiDAR by enabling photon-efficient 3D sensing under challenging conditions such as long-range operation, low-albedo targets, and limited signal returns. However, developing SPL perception models for real-world robotic applications remains difficult because annotated SPL data are costly to obtain and model performance can vary substantially across imaging conditions. In this paper, we present the first active learning framework tailored to the SPL sensing modality rather than a specific downstream task. Our method introduces a physics-grounded, imaging condition-aware sampling strategy that uses synthetic SPL variants to characterize how candidate samples respond to changes in sensing conditions. By jointly modeling prediction uncertainty, sample diversity, and sensitivity to photon-level imaging variations, the proposed approach prioritizes samples that are informative for improving labeling efficiency and robustness. Extensive experiments on synthetic and real-world SPL datasets demonstrate that our method substantially reduces annotation requirements while maintaining strong performance across image-level and dense prediction settings. On synthetic data, our approach achieves 97% classification accuracy using only 1.5% labeled samples. On real-world data, it maintains 90% accuracy with 8.2% labeled samples, outperforming the strongest baseline by 6%. Segmentation results further show that the same condition-aware acquisition principle improves annotation efficiency and robustness across imaging conditions. These results establish a modality-aware active learning strategy for data-efficient SPL perception, with the potential to extend to a broader range of downstream tasks.