AHCI RESEARCH GROUP

Publications

Papers published in international journals,
proceedings of conferences, workshops and books.

OUR RESEARCH

Scientific Publications

How to

Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.

Show all

2025

Zeng, S. -Y.; Liang, T. -Y.

PartConverter: A Part-Oriented Transformation Framework for Point Clouds Journal Article

In: IET Image Processing, vol. 19, no. 1, 2025, ISSN: 17519659 (ISSN).

Abstract | Links | BibTeX | Tags: 3D modeling, 3D models, 3d-modeling, Adversarial networks, attention mechanism, Attention mechanisms, Auto encoders, Cloud transformations, Generative Adversarial Network, Part assembler, Part-oriented, Point cloud transformation, Point-clouds

@article{zeng_partconverter_2025,

title = {PartConverter: A Part-Oriented Transformation Framework for Point Clouds},

author = {S. -Y. Zeng and T. -Y. Liang},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105005775417&doi=10.1049%2fipr2.70104&partnerID=40&md5=1ee3178fd6b4a03bc7e299e1292e9694},

doi = {10.1049/ipr2.70104},

issn = {17519659 (ISSN)},

year  = {2025},

date = {2025-01-01},

journal = {IET Image Processing},

volume = {19},

number = {1},

abstract = {With generative AI technologies advancing rapidly, the capabilities for 3D model generation and transformation are expanding across industries like manufacturing, healthcare, and virtual reality. However, existing methods based on generative adversarial networks (GANs), autoencoders, or transformers still have notable limitations. They primarily generate entire objects without providing flexibility for independent part transformation or precise control over model components. These constraints pose challenges for applications requiring complex object manipulation and fine-grained adjustments. To overcome these limitations, we propose PartConverter, a novel part-oriented point cloud transformation framework emphasizing flexibility and precision in 3D model transformations. PartConverter leverages attention mechanisms and autoencoders to capture crucial details within each part while modeling the relationships between components, thereby enabling highly customizable, part-wise transformations that maintain overall consistency. Additionally, our part assembler ensures that transformed parts align coherently, resulting in a consistent and realistic final 3D shape. This framework significantly enhances control over detailed part modeling, increasing the flexibility and efficiency of 3D model transformation workflows. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.},

keywords = {3D modeling, 3D models, 3d-modeling, Adversarial networks, attention mechanism, Attention mechanisms, Auto encoders, Cloud transformations, Generative Adversarial Network, Part assembler, Part-oriented, Point cloud transformation, Point-clouds},

pubstate = {published},

tppubtype = {article}

}