Saved in:
Bibliographic Details
Main Authors: Zhang, Haomiao, Li, Zhangyuan, Piao, Yanling, Li, Zhi, Wang, Xiaodong, Cao, Miao, Su, Xiongfei, Song, Qiang, Yuan, Xin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.21657
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918132645363712
author Zhang, Haomiao
Li, Zhangyuan
Piao, Yanling
Li, Zhi
Wang, Xiaodong
Cao, Miao
Su, Xiongfei
Song, Qiang
Yuan, Xin
author_facet Zhang, Haomiao
Li, Zhangyuan
Piao, Yanling
Li, Zhi
Wang, Xiaodong
Cao, Miao
Su, Xiongfei
Song, Qiang
Yuan, Xin
contents Computer-generated holography (CGH) has gained wide attention with deep learning-based algorithms. However, due to its nonlinear and ill-posed nature, challenges remain in achieving accurate and stable reconstruction. Specifically, ($i$) the widely used end-to-end networks treat the reconstruction model as a black box, ignoring underlying physical relationships, which reduces interpretability and flexibility. ($ii$) CNN-based CGH algorithms have limited receptive fields, hindering their ability to capture long-range dependencies and global context. ($iii$) Angular spectrum method (ASM)-based models are constrained to finite near-fields.In this paper, we propose a Deep Unfolding Network (DUN) that decomposes gradient descent into two modules: an adaptive bandwidth-preserving model (ABPM) and a phase-domain complex-valued denoiser (PCD), providing more flexibility. ABPM allows for wider working distances compared to ASM-based methods. At the same time, PCD leverages its complex-valued deformable self-attention module to capture global features and enhance performance, achieving a PSNR over 35 dB. Experiments on simulated and real data show state-of-the-art results.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21657
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation
Zhang, Haomiao
Li, Zhangyuan
Piao, Yanling
Li, Zhi
Wang, Xiaodong
Cao, Miao
Su, Xiongfei
Song, Qiang
Yuan, Xin
Computer Vision and Pattern Recognition
Computer-generated holography (CGH) has gained wide attention with deep learning-based algorithms. However, due to its nonlinear and ill-posed nature, challenges remain in achieving accurate and stable reconstruction. Specifically, ($i$) the widely used end-to-end networks treat the reconstruction model as a black box, ignoring underlying physical relationships, which reduces interpretability and flexibility. ($ii$) CNN-based CGH algorithms have limited receptive fields, hindering their ability to capture long-range dependencies and global context. ($iii$) Angular spectrum method (ASM)-based models are constrained to finite near-fields.In this paper, we propose a Deep Unfolding Network (DUN) that decomposes gradient descent into two modules: an adaptive bandwidth-preserving model (ABPM) and a phase-domain complex-valued denoiser (PCD), providing more flexibility. ABPM allows for wider working distances compared to ASM-based methods. At the same time, PCD leverages its complex-valued deformable self-attention module to capture global features and enhance performance, achieving a PSNR over 35 dB. Experiments on simulated and real data show state-of-the-art results.
title Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.21657