Efficient Additive 3D Modeling from Single Images via Layered Morphing Techniques

A novel technique for single-image-driven rapid additive 3D modeling is presented, integrating principles of 3D printing with topological relationships between adjacent layers. By incorporating innovative curve morphing techniques, efficient transformation from a single image to complex three-dimensional models is achieved. Experimental evaluations demonstrate that superior performance in modeling efficiency, geometric accuracy, and visual fidelity is attained, particularly for regular geometric shapes and transitional forms. While potential for refinement in detailed reconstruction of complex cultural artifacts is noted, competitive overall results are still observed. Compared to traditional manual modeling, significant enhancements in speed are realized, while high levels of accuracy and appearance similarity are maintained, and data requirements along with computational complexity are substantially reduced. Practical solutions for rapid product design, digital heritage preservation, and augmented/virtual reality (AR/VR) applications are provided, with optimized layer structuring and topological control addressing precision limitations inherent in deep learning approaches. This research advances the field of 3D modeling by offering a robust, efficient framework with broad theoretical and practical implications.

Authors

Institutions

Publication Details

Published
2025-03-21
DOI
https://doi.org/10.1109/iscait64916.2025.11010556
Primary Topic
3D Shape Modeling and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Efficient Additive 3D Modeling from Single Images via Layered Morphing Techniques

Hengheng Zhao, Ping Huang, Xiying Wang, Ruolong Wang
3D Shape Modeling and Analysis
article

Efficient Additive 3D Modeling from Single Images via Layered Morphing Techniques

Hengheng Zhao, Ping Huang, Xiying Wang, Ruolong Wang
article en

Abstract

A novel technique for single-image-driven rapid additive 3D modeling is presented, integrating principles of 3D printing with topological relationships between adjacent layers. By incorporating innovative curve morphing techniques, efficient transformation from a single image to complex three-dimensional models is achieved. Experimental evaluations demonstrate that superior performance in modeling efficiency, geometric accuracy, and visual fidelity is attained, particularly for regular geometric shapes and transitional forms. While potential for refinement in detailed reconstruction of complex cultural artifacts is noted, competitive overall results are still observed. Compared to traditional manual modeling, significant enhancements in speed are realized, while high levels of accuracy and appearance similarity are maintained, and data requirements along with computational complexity are substantially reduced. Practical solutions for rapid product design, digital heritage preservation, and augmented/virtual reality (AR/VR) applications are provided, with optimized layer structuring and topological control addressing precision limitations inherent in deep learning approaches. This research advances the field of 3D modeling by offering a robust, efficient framework with broad theoretical and practical implications.

Xiamen Tobacco Industry (China) (CN), Xiamen University of Technology (CN)
Openalex Percentile: Top 87%
3D Shape Modeling and Analysis
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.

Efficient Additive 3D Modeling from Single Images via Layered Morphing Techniques — Hengheng Zhao, Ping Huang, et al. · (2025) | TGRS Research Map | TGRS