P-Hologen: An End-to-End Generative Framework for Phase-Only Holograms

2024-03-29

Computer graphics forum (Print)

AI Summary

To address computational redundancy and efficiency bottlenecks in phase-only hologram (POH) generation—arising from decoupled image prior modeling and post-hoc phase conversion—this paper proposes P-Hologen, the first end-to-end POH generation framework. Instead of the conventional two-stage “image synthesis + phase retrieval” pipeline, P-Hologen directly models the complex-valued phase distribution of POHs. It innovatively integrates the angular spectrum propagation model into the VQ-VAE training process, yielding a differentiable latent space explicitly tailored to holographic phase characteristics. The framework enables high-fidelity, diverse hologram generation without requiring explicit image priors, while supporting semantic-controllable synthesis and editing. Experiments demonstrate that P-Hologen significantly outperforms state-of-the-art methods in both reconstruction fidelity and inference speed. The code is publicly released to advance practical research in holographic generative modeling.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Holography stands at the forefront of visual technology, offering immersive, three‐dimensional visualizations through the manipulation of light wave amplitude and phase. Although generative models have been extensively explored in the image domain, their application to holograms remains relatively underexplored due to the inherent complexity of phase learning. Exploiting generative models for holograms offers exciting opportunities for advancing innovation and creativity, such as semantic‐aware hologram generation and editing. Currently, the most viable approach for utilizing generative models in the hologram domain involves integrating an image‐based generative model with an image‐to‐hologram conversion model, which comes at the cost of increased computational complexity and inefficiency. To tackle this problem, we introduce P‐Hologen, the first end‐to‐end generative framework designed for phase‐only holograms (POHs). P‐Hologen employs vector quantized variational autoencoders to capture the complex distributions of POHs. It also integrates the angular spectrum method into the training process, constructing latent spaces for complex phase data using strategies from the image processing domain. Extensive experiments demonstrate that P‐Hologen achieves superior quality and computational efficiency compared to the existing methods. Furthermore, our model generates high‐quality unseen, diverse holographic content from its learned latent space without requiring pre‐existing images. Our work paves the way for new applications and methodologies in holographic content creation, opening a new era in the exploration of generative holographic content. The code for our paper is publicly available on https://github.com/james0223/P-Hologen.

Problem

• Develops end-to-end generative framework for phase-only holograms
• Addresses complexity and inefficiency in hologram generation
• Enables high-quality diverse holographic content creation

Innovation

• End-to-end generative framework for phase-only holograms
• Uses vector quantized variational autoencoders for POHs
• Integrates angular spectrum method in training