Binyu Nie — accepted AI-conference papers

2026

SonarGAN: A Progressive GAN Framework for Sonar Image Denoising under Multi-Type Noises

Zhangrui Hu, Yunxuan Feng, Binyu Nie, Lei Yan, Wenjie Lu, Liang Hu

ICRA 2026poster

Forward-looking sonar is essential for underwater perception especially in turbid waters, yet its images are often strongly degraded by various noises, including speckle, sidelobe, and structural noises, which severely hinder downstream tasks such as underwater reconstruction, positioning, and navig…

Cited by 0 Scholar ↗

2024

Differentiable Space Carving for 3D Reconstruction Using Imaging Sonar

Yunxuan Feng, Wenjie Lu, Haowen Gao, Binyu Nie, Kaiyang Lin, Liang Hu

RA-L 2024

Effective 3D reconstruction utilizing imaging sonars is vital for underwater robots, particularly in turbid water conditions. The absence of elevation angles in acoustic echo measurements significantly slows down the Neural Radiance Field (NeRF) method. This is attributed to the differentiable rende

Cited by 12 Source ↗Scholar ↗