Songyang Gao

Songyang Gao

Senior@NCU AI | Mphil@HKUST(GZ) (Wechat: rxsy2003)

Publications

You can also find my articles on my Google Scholar profile.

DMEDH: diffusion model-boosted multiplane extrapolation for digital holographic reconstruction (JCR-Q2, First author)

Published in Optics Express, 2024

To attain high-quality image reconstruction, a diffusion model-boosted multiplane extrapolation for digital holographic reconstruction (DMEDH) algorithm is proposed.

Recommended citation: Gao S, Xv W, Wu X, Liu J, Wang B, Wu T, Wan W, Liu Q. DMEDH: diffusion model-boosted multiplane extrapolation for digital holographic reconstruction. Optics Express. 2024, 32(18):31920-31938. https://doi.org/10.1364/OE.531147
Download Paper

HoloDiffusion: Sparse Digital Holographic Reconstruction via Diffusion Modeling (JCR-Q3, Co-first author)

Published in Photonics, 2024

An image reconstruction method is proposed that combines physical constraint characteristics of the imaging object with a score-based diffusion model, aiming to enhance the imaging accuracy of digital holography technology with extremely sparse sensor arrays.

Recommended citation: Zhang L, Gao S, Tong M, Huang Y, Zhang Z, Wan W, Liu Q. HoloDiffusion: Sparse Digital Holographic Reconstruction via Diffusion Modeling. Photonics. 2024, 11(4):388. https://doi.org/10.3390/photonics11040388
Download Paper

ARA-Net: An Attention-Aware Retinal Atrophy Segmentation Network Coping With Fundus Images (JCR-Q2, Third author)

Published in Frontiers in Neuroscience, 2023

In this paper, An attention-aware retinal atrophy segmentation network (ARA-Net) is proposed to segment retinal atrophy areas from the 2D fundus image.

Recommended citation: Chen L, Zhou YY, Gao SY, Li MY, Tan H, Wan ZJ. ARA-net: an attention-aware retinal atrophy segmentation network coping with fundus images. Frontiers in Neuroscience, 2023, 17: 1174937.
Download Paper