GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation

Meshes are essential for representing 3D assets across many industrial applications and serve as the standard input for graphics rendering pipelines. However, their irregular structure makes their creation and manipulation both time-consuming and labor-intensive. In this paper, we introduce GetMesh, a new generative model designed for mesh generation and manipulation across various categories. Utilizing a dynamic number of points as a latent representation, which is then organized into a triplane representation, GetMesh generates meshes with geometric details, sharp features as well as textures. This model significantly outperforms existing methods for both single-category and multi-category generation. Moreover, GetMesh offers unparalleled fine-grained control over the generation process, enabling intuitive, efficient, and robust modifications. These include changing global or local mesh topologies, adding or removing mesh parts, and combining mesh parts across categories through adjustments in the number, positions or features of the latent points.

Authors

Institutions

Publication Details

Journal
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2025-01-01
DOI
https://doi.org/10.1109/tpami.2025.3594478
Citations
1
Primary Topic
Advanced Malware Detection Techniques
Type
article
Field-Weighted Citation Impact
1.49
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation

Dahua Lin, Lei Bai, K. J. Ray Liu, Ying He et al.
1 citations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Advanced Malware Detection Techniques
1.49
article

GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation

Dahua Lin, Lei Bai, K. J. Ray Liu, Ying He, Zhaoyang Lyu, Bo Dai, Ben Fei, Ya Zhang, Jinyi Wang, Xudong Xu, Weidong Yang
article en
1 citations

Abstract

Meshes are essential for representing 3D assets across many industrial applications and serve as the standard input for graphics rendering pipelines. However, their irregular structure makes their creation and manipulation both time-consuming and labor-intensive. In this paper, we introduce GetMesh, a new generative model designed for mesh generation and manipulation across various categories. Utilizing a dynamic number of points as a latent representation, which is then organized into a triplane representation, GetMesh generates meshes with geometric details, sharp features as well as textures. This model significantly outperforms existing methods for both single-category and multi-category generation. Moreover, GetMesh offers unparalleled fine-grained control over the generation process, enabling intuitive, efficient, and robust modifications. These include changing global or local mesh topologies, adding or removing mesh parts, and combining mesh parts across categories through adjustments in the number, positions or features of the latent points.

IEEE Transactions on Pattern Analysis and Machine IntelligenceVol. PP
Nanyang Technological University (SG), Chinese University of Hong Kong (HK), Shanghai Jiao Tong University (CN), Fudan University (CN), Shanghai Artificial Intelligence Laboratory (CN)
Openalex Percentile: Top 16%
Advanced Malware Detection Techniques
1.49
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.

GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation — Dahua Lin, Lei Bai, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence (2025) | TGRS Research Map | TGRS