AI Paper Atlas

Research map / 3D vision / Gaussian splatting

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

Yicheng Zhan, Xiangjun Gao, Long Quan, Kaan Akşit

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add structural guidance in POH conversion (vs independently optimized Random POH) (ablation)Complex-valued 2D Gaussians · Random POHPSNR: 19.1 -> 30.6Improved
add structural guidance in POH conversion (ablation)Complex-valued 2D Gaussians · Random POHLPIPS: 0.52 -> 0.22Improved
use unified complex-valued Gaussians instead of naive paired real Gaussians (ablation)Complex-valued 2D Gaussians · Gaussian definitionPSNR: 25.5 -> 31.8Improved
use unified complex-valued Gaussians instead of naive paired real Gaussians (ablation)Complex-valued 2D Gaussians · Gaussian definitionParams (M): 1.2 -> 0.8Improved
use unified complex-valued Gaussians instead of naive paired real Gaussians (ablation)Complex-valued 2D Gaussians · Gaussian definitionRender (ms): 20.1 -> 2.13Improved
keep amplitude decomposed into opacity alpha and color c (ablation)Complex-valued 2D Gaussians · 50 DIV2K imagesPSNR: 29.5 -> 30.7Improved
keep amplitude decomposed into opacity alpha and color c (ablation)Complex-valued 2D Gaussians · 50 DIV2K imagesLPIPS: 0.40 -> 0.33Improved
reduce parameters 2:1 vs dense per-pixel (ablation)Complex-valued 2D Gaussians · Parameter reduction ratioPSNR: 32.3 -> 31.9No clear effect
reduce parameters 5:1 vs dense per-pixel (ablation)Complex-valued 2D Gaussians · Parameter reduction ratioPSNR: 32.3 -> 30.7Hurt
reduce parameters 10:1 vs dense per-pixel (ablation)Complex-valued 2D Gaussians · Parameter reduction ratioPSNR: 32.3 -> 29.4Hurt
reduce parameters 10:1 vs dense per-pixel (ablation)Complex-valued 2D Gaussians · Parameter reduction ratioRender (ms): 4.02 -> 1.72Improved
use CUDA kernel instead of PyTorch implementationComplex-valued 2D Gaussians · runtimeVRAM: 28.9% to 35.6% memory savingsImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy