Spatial relationships guide semantic component extraction from Gaussian splatting of traditional Chinese timber architecture

Three-dimensional Gaussian splatting enables photorealistic documentation of architectural heritage, but extracting semantically accurate components remains challenging. We propose a framework for traditional Chinese timber architecture that combines spatial relationship-guided annotation with semantic–appearance decoupled Gaussian extraction. A spatial relationship graph guides a multimodal large language model in distinguishing visually similar components. Semantic assignments and filtering weights are then learned while keeping the reconstructed scene parameters fixed. On a Qing-dynasty timber-frame building with 22 component categories, the framework increases image-level mean intersection over union from 69.03% to 85.72% and extracted-object mean intersection over union from 28.01% to 69.24% compared with Heritage-3DGS. Average isolated-component peak signal-to-noise ratio increases from 17.05 to 24.30 dB, while full-scene rendering quality is preserved. The framework provides independently renderable component categories for semantic access to photorealistic architectural heritage records.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-18
DOI
https://doi.org/10.21203/rs.3.rs-11518276/v1
Primary Topic
3D Surveying and Cultural Heritage
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Spatial relationships guide semantic component extraction from Gaussian splatting of traditional Chinese timber architecture

Dong Li, Xingxing Xiao, Weifeng Ma, Ming Huang et al.
3 links
Research Square
3D Surveying and Cultural Heritage
preprint

Spatial relationships guide semantic component extraction from Gaussian splatting of traditional Chinese timber architecture

Dong Li, Xingxing Xiao, Weifeng Ma, Ming Huang, Lei Wang
preprint en

Abstract

Three-dimensional Gaussian splatting enables photorealistic documentation of architectural heritage, but extracting semantically accurate components remains challenging. We propose a framework for traditional Chinese timber architecture that combines spatial relationship-guided annotation with semantic–appearance decoupled Gaussian extraction. A spatial relationship graph guides a multimodal large language model in distinguishing visually similar components. Semantic assignments and filtering weights are then learned while keeping the reconstructed scene parameters fixed. On a Qing-dynasty timber-frame building with 22 component categories, the framework increases image-level mean intersection over union from 69.03% to 85.72% and extracted-object mean intersection over union from 28.01% to 69.24% compared with Heritage-3DGS. Average isolated-component peak signal-to-noise ratio increases from 17.05 to 24.30 dB, while full-scene rendering quality is preserved. The framework provides independently renderable component categories for semantic access to photorealistic architectural heritage records.

Research Square
Yunnan Normal University (CN), Beijing University of Civil Engineering and Architecture (CN)
National Natural Science Foundation of China, National Science and Technology Major Project
3D Surveying and Cultural Heritage
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.

Laika access coming soon