Xiangjun Yin — accepted AI-conference papers

2024

LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging

Haoyang Ge, Qiao Feng, Hailong Jia, Xiongzheng Li, Xiangjun Yin, You Zhou +2

CVPR 2024poster

Human pose and shape (HPS) estimation with lensless imaging is not only beneficial to privacy protection but also can be used in covert surveillance scenarios due to the small size and simple structure of this device. However this task presents significant challenges due to the inherent ambiguity of…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients

Xingyu Cui, Huanjing Yue, Song Li, Xiangjun Yin, Yusen Hou, Yun Meng +3

NeurIPS 2024poster

Non-line-of-sight (NLOS) imaging allows for seeing hidden scenes around corners through active sensing. Most previous algorithms for NLOS reconstruction require dense transients acquired through regular scans over a large relay surface, which limits their applicability in realistic scenarios with ir…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗