English

Point upsampling networks for single-photon sensing

Optics 2025-08-19 v1 Computer Vision and Pattern Recognition

Abstract

Single-photon sensing has generated great interest as a prominent technique of long-distance and ultra-sensitive imaging, however, it tends to yield sparse and spatially biased point clouds, thus limiting its practical utility. In this work, we propose using point upsampling networks to increase point density and reduce spatial distortion in single-photon point cloud. Particularly, our network is built on the state space model which integrates a multi-path scanning mechanism to enrich spatial context, a bidirectional Mamba backbone to capture global geometry and local details, and an adaptive upsample shift module to correct offset-induced distortions. Extensive experiments are implemented on commonly-used datasets to confirm its high reconstruction accuracy and strong robustness to the distortion noise, and also on real-world data to demonstrate that our model is able to generate visually consistent, detail-preserving, and noise suppressed point clouds. Our work is the first to establish the upsampling framework for single-photon sensing, and hence opens a new avenue for single-photon sensing and its practical applications in the downstreaming tasks.

Keywords

Cite

@article{arxiv.2508.12986,
  title  = {Point upsampling networks for single-photon sensing},
  author = {Jinyi Liu and Guoyang Zhao and Lijun Liu and Yiguang Hong and Weiping Zhang and Shuming Cheng},
  journal= {arXiv preprint arXiv:2508.12986},
  year   = {2025}
}

Comments

13 pages, 8 figures, any comments are welcome

R2 v1 2026-07-01T04:54:57.665Z