3D Gaussian rasterization for direct rendering of view‐multiplexed images on multiview displays

Abstract Real‐time rendering of three‐dimensional scenes is essential for interactive, realistic display systems. Recently, representations based on 3D Gaussian primitives have emerged as a promising approach for novel view synthesis, offering both photorealistic image quality and real‐time rendering. However, extending such renderers to autostereoscopic multiview displays is not straightforward because each subpixel must be rendered from a different viewpoint, whereas conventional renderers exploit shared viewport information to achieve efficiency. In this paper, we propose a rasterization method for 3D Gaussian‐based representations that enables efficient rendering for multiview displays. By leveraging prior knowledge of the target viewport layout, the proposed method achieves an approximately 11 times speedup compared with the baseline without compromising image quality. We analyze the rendering performance of the proposed method under various combinations of renderer configurations and 3D scene datasets, demonstrating its potential for real‐time multiview rendering.

Authors

Institutions

Publication Details

Journal
ETRI Journal
Published
2026-02-21
DOI
https://doi.org/10.4218/etrij.2025-0246
Primary Topic
Advanced Optical Imaging Technologies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

3D Gaussian rasterization for direct rendering of view‐multiplexed images on multiview displays

Kyeongbo Kong, Joonsoo Kim, Kugjin Yun, Hyeongju Mun et al.
ETRI Journal
Advanced Optical Imaging Technologies
article

3D Gaussian rasterization for direct rendering of view‐multiplexed images on multiview displays

Kyeongbo Kong, Joonsoo Kim, Kugjin Yun, Hyeongju Mun, Hyon‐Gon Choo
article en

Abstract

Abstract Real‐time rendering of three‐dimensional scenes is essential for interactive, realistic display systems. Recently, representations based on 3D Gaussian primitives have emerged as a promising approach for novel view synthesis, offering both photorealistic image quality and real‐time rendering. However, extending such renderers to autostereoscopic multiview displays is not straightforward because each subpixel must be rendered from a different viewpoint, whereas conventional renderers exploit shared viewport information to achieve efficiency. In this paper, we propose a rasterization method for 3D Gaussian‐based representations that enables efficient rendering for multiview displays. By leveraging prior knowledge of the target viewport layout, the proposed method achieves an approximately 11 times speedup compared with the baseline without compromising image quality. We analyze the rendering performance of the proposed method under various combinations of renderer configurations and 3D scene datasets, demonstrating its potential for real‐time multiview rendering.

ETRI Journal
Electronics and Telecommunications Research Institute (KR), Pusan National University (KR)
Openalex Percentile: Top 54%
Advanced Optical Imaging Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

3D Gaussian rasterization for direct rendering of view‐multiplexed images on multiview displays — Kyeongbo Kong, Joonsoo Kim, et al. · ETRI Journal (2026) | TGRS Research Map | TGRS