Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.12986 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912541521739776 |
|---|---|
| author | Liu, Jinyi Zhao, Guoyang Liu, Lijun Hong, Yiguang Zhang, Weiping Cheng, Shuming |
| author_facet | Liu, Jinyi Zhao, Guoyang Liu, Lijun Hong, Yiguang Zhang, Weiping Cheng, Shuming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12986 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Point upsampling networks for single-photon sensing Liu, Jinyi Zhao, Guoyang Liu, Lijun Hong, Yiguang Zhang, Weiping Cheng, Shuming Optics Computer Vision and Pattern Recognition 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. |
| title | Point upsampling networks for single-photon sensing |
| topic | Optics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.12986 |