Xinyue Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinyue Wei has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Hao Su
University of California San Diego, San Diego, USA
6 shared publications - Minghua Liu
Hillbot, Sunnyvale, USA
4 shared publications - Ruoxi Shi
University of California San Diego, San Diego, USA
4 shared publications - Fanbo Xiang
Sudo GmbH, La Jolla, USA
2 shared publications - Xiaoshuai Zhang
Hillbot, Sunnyvale, USA
2 shared publications - Zexiang Xu
Sudo GmbH, La Jolla, USA
2 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
CuACD: A Fully GPU-Resident Approximate Convex Decomposition
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessCuACD: A Fully GPU-Resident Approximate Convex Decomposition
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
LARM: A Large Articulated Object Reconstruction Model
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessLARM: A Large Articulated Object Reconstruction Model
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
PartUV: Part-Based UV Unwrapping of 3D Meshes
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessPartUV: Part-Based UV Unwrapping of 3D Meshes
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessFreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion
- 11 October 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (7)
PaMO: Parallel Mesh Optimization for Intersection‐Free Low‐Poly Modeling on the GPU
Reducing the triangle count in complex 3D models is a basic geometry preprocessing step in graphics pipelines such as efficient rendering and interactive editing. However, most existing mesh simplification methods exhibit a few issues. Firstly, they often lead to self‐intersections during decimation, a major issue for applications such as 3D printing and soft‐body simulation. Second, to perform simplification on a mesh in the wild, one would first need to perform re‐meshing, which often suffers from surface shifts and losses of sharp features. Finally, existing re‐meshing and simplification methods can take minutes when processing large‐scale meshes, limiting their applications in practice. To address the challenges, we introduce a novel GPU‐based mesh optimization approach containing three key components: (1) a parallel re‐meshing algorithm to turn meshes in the wild into watertight, manifold, and intersection‐free ones, and reduce the prevalence of poorly shaped triangles; (2) a robust parallel simplification algorithm with intersection‐free guarantees; (3) an optimization‐based safe projection algorithm to realign the simplified mesh with the input, eliminating the surface shift introduced by re‐meshing and recovering the original sharp features. The algorithm demonstrates remarkable efficiency, simplifying a 2‐million‐face mesh to 20k triangles in 3 seconds on RTX4090. We evaluated the approach on the Thingi10K dataset and showcased its exceptional performance in geometry preservation and speed. https://seonghunn.github.io/pamo/
- 11 October 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (7)
PaMO: Parallel Mesh Optimization for Intersection‐Free Low‐Poly Modeling on the GPU
Reducing the triangle count in complex 3D models is a basic geometry preprocessing step in graphics pipelines such as efficient rendering and interactive editing. However, most existing mesh simplification methods exhibit a few issues. Firstly, they often lead to self‐intersections during decimation, a major issue for applications such as 3D printing and soft‐body simulation. Second, to perform simplification on a mesh in the wild, one would first need to perform re‐meshing, which often suffers from surface shifts and losses of sharp features. Finally, existing re‐meshing and simplification methods can take minutes when processing large‐scale meshes, limiting their applications in practice. To address the challenges, we introduce a novel GPU‐based mesh optimization approach containing three key components: (1) a parallel re‐meshing algorithm to turn meshes in the wild into watertight, manifold, and intersection‐free ones, and reduce the prevalence of poorly shaped triangles; (2) a robust parallel simplification algorithm with intersection‐free guarantees; (3) an optimization‐based safe projection algorithm to realign the simplified mesh with the input, eliminating the surface shift introduced by re‐meshing and recovering the original sharp features. The algorithm demonstrates remarkable efficiency, simplifying a 2‐million‐face mesh to 20k triangles in 3 seconds on RTX4090. We evaluated the approach on the Thingi10K dataset and showcased its exceptional performance in geometry preservation and speed. https://seonghunn.github.io/pamo/
- Open Access
- 26 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-12
Dictionary Fields: Learning a Neural Basis Decomposition
We present Dictionary Fields, a novel neural representation which decomposes a signal into a product of factors, each represented by a classical or neural field representation, operating on transformed input coordinates. More specifically, we factorize a signal into a coefficient field and a basis field, and exploit periodic coordinate transformations to apply the same basis functions across multiple locations and scales. Our experiments show that Dictionary Fields lead to improvements in approximation quality, compactness, and training time when compared to previous fast reconstruction methods. Experimentally, our representation achieves better image approximation quality on 2D image regression tasks, higher geometric quality when reconstructing 3D signed distance fields, and higher compactness for radiance field reconstruction tasks. Furthermore, Dictionary Fields enable generalization to unseen images/3D scenes by sharing bases across signals during training which greatly benefits use cases such as image regression from partial observations and few-shot radiance field reconstruction.
- 26 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-12
Open AccessDictionary Fields: Learning a Neural Basis Decomposition
We present Dictionary Fields, a novel neural representation which decomposes a signal into a product of factors, each represented by a classical or neural field representation, operating on transformed input coordinates. More specifically, we factorize a signal into a coefficient field and a basis field, and exploit periodic coordinate transformations to apply the same basis functions across multiple locations and scales. Our experiments show that Dictionary Fields lead to improvements in approximation quality, compactness, and training time when compared to previous fast reconstruction methods. Experimentally, our representation achieves better image approximation quality on 2D image regression tasks, higher geometric quality when reconstructing 3D signed distance fields, and higher compactness for radiance field reconstruction tasks. Furthermore, Dictionary Fields enable generalization to unseen images/3D scenes by sharing bases across signals during training which greatly benefits use cases such as image regression from partial observations and few-shot radiance field reconstruction.