Score: 2

Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation

Published: August 29, 2025 | arXiv ID: 2508.21657v1

By: Haomiao Zhang , Zhangyuan Li , Yanling Piao and more

Potential Business Impact:

Makes holograms clearer and more realistic.

Business Areas:
Field-Programmable Gate Array (FPGA) Hardware

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.

Repos / Data Links

Page Count
6 pages

Category
Computer Science:
CV and Pattern Recognition