Qingxuan Lv — accepted AI-conference papers

2025

FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-from-gradients

Jiaqi Leng, Yakun Ju, Yuanxu Duan, Jiangnan Zhang, Qingxuan Lv, Zuxuan Wu +1

AAAI 2025technical

Surface-from-gradients (SfG) aims to recover a three-dimensional (3D) surface from its gradients. Traditional methods encounter significant challenges in achieving high accuracy and handling high-resolution inputs, particularly facing the complex nature of discontinuities and the inefficiencies asso…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Embedded Attention Network for Semantic Segmentation

Qingxuan Lv, Mingzhe Feng, Xin Sun, Junyu Dong, Changrui Chen, Yu Zhang

RA-L 2022

Semantic segmentation, as a fundamental task in computer vision, is capable of providing perception ability in many robot applications, such as automatic navigation. To enhance the segmentation accuracy, self-attention mechanism is adopted as a key technique for capturing the long-range dependency a

Cited by 1 Source ↗Scholar ↗