Complex-Valued 2D Gaussian Representation for Computer-Generated Holography

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhan, Yicheng, Gao, Xiangjun, Quan, Long, Akşit, Kaan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914164089290752
author Zhan, Yicheng
Gao, Xiangjun
Quan, Long
Akşit, Kaan
author_facet Zhan, Yicheng
Gao, Xiangjun
Quan, Long
Akşit, Kaan
contents We propose a new hologram representation based on structured complex-valued 2D Gaussian primitives, which replaces per-pixel information storage and reduces the parameter search space by up to 10:1. To enable end-to-end training, we develop a differentiable rasterizer for our representation, integrated with a GPU-optimized light propagation kernel in free space. Our extensive experiments show that our method achieves up to 2.5x lower VRAM usage and 50% faster optimization while producing higher-fidelity reconstructions than existing methods. We further introduce a conversion procedure that adapts our representation to practical hologram formats, including smooth and random phase-only holograms. Our experiments show that this procedure can effectively suppress noise artifacts observed in previous methods. By reducing the hologram parameter search space, our representation enables a more scalable hologram estimation in the next-generation computer-generated holography systems.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15022
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Complex-Valued 2D Gaussian Representation for Computer-Generated Holography
Zhan, Yicheng
Gao, Xiangjun
Quan, Long
Akşit, Kaan
Computer Vision and Pattern Recognition
Graphics
Machine Learning
We propose a new hologram representation based on structured complex-valued 2D Gaussian primitives, which replaces per-pixel information storage and reduces the parameter search space by up to 10:1. To enable end-to-end training, we develop a differentiable rasterizer for our representation, integrated with a GPU-optimized light propagation kernel in free space. Our extensive experiments show that our method achieves up to 2.5x lower VRAM usage and 50% faster optimization while producing higher-fidelity reconstructions than existing methods. We further introduce a conversion procedure that adapts our representation to practical hologram formats, including smooth and random phase-only holograms. Our experiments show that this procedure can effectively suppress noise artifacts observed in previous methods. By reducing the hologram parameter search space, our representation enables a more scalable hologram estimation in the next-generation computer-generated holography systems.
title Complex-Valued 2D Gaussian Representation for Computer-Generated Holography
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
url https://arxiv.org/abs/2511.15022