1 citations · 2 across the 11 of their papers we have counts for
14 papers
Projective Normal Fields: A Convex Optimization Method for Constructing Smooth UDFs
Jiayi Kong, Chen Zong, Fei Hou +3
Constructing a smooth approximation of an unsigned distance field (UDF) from a raw point cloud is challenging because the input provides neither surface connectivity nor consistent…
Beyond UV Mapping: Mesh Texture Compression via Surface-Aligned Texture Fields
Jianqiang Wang, Junhui Hou, Siyu Ren +2
Mesh texture compression typically relies on 2D UV atlases, whose chart discontinuities and mapping overhead can limit coding efficiency. To tackle this challenge, we introduce Tex…
QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
Yiheng Zhang, Zhe Zhu, Tingrui Shen +11
The generation of production-ready quad-dominant meshes is a cornerstone of modern 3D content creation. Generating anisotropic quad-dominant meshes from point clouds is challenging…
Metric--Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point Clouds
Jiayi Kong, Xuhui Chen, Chen Zong +4
Neural Signed Distance Functions (SDFs) excel at reconstructing watertight manifolds but fail on thin structures and open boundaries due to strict inside--outside constraints. Conv…
SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
Chuanxiang Yang, Junhui Hou, Yuan Liu +5
Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost of network evaluations. We observe that…
Joint Orientation and Weight Optimization for Robust Watertight Surface Reconstruction via Dirichlet-Regularized Winding Fields
Jiaze Li, Daisheng Jin, Fei Hou +5
We propose Dirichlet Winding Reconstruction (DiWR), a robust method for reconstructing watertight surfaces from unoriented point clouds with non-uniform sampling, noise, and outlie…
T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation
Chuanxiang Yang, Yuanfeng Zhou, Guangshun Wei +4
Level-of-detail (LoD) representation is critical for efficiently modeling and transmitting various types of signals, such as images and 3D shapes. In this work, we propose a novel…
FlexPara: Flexible Neural Surface Parameterization
Yuming Zhao, Qijian Zhang, Junhui Hou +3
Surface parameterization is a fundamental geometry processing task, laying the foundations for the visual presentation of 3D assets and numerous downstream shape analysis scenarios…
SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation
Qijian Zhang, Xiaozheng Jian, Xuan Zhang +2
Conventional production workflow of high-precision mesh assets necessitates a cumbersome and laborious process of manual sculpting by specialized 3D artists/modelers. The recent ye…
Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds
Chuanxiang Yang, Yuanfeng Zhou, Guangshun Wei +4
As commonly used implicit geometry representations, the signed distance function (SDF) is limited to modeling watertight shapes, while the unsigned distance function (UDF) is capab…
Flatten Anything: Unsupervised Neural Surface Parameterization
Qijian Zhang, Junhui Hou, Wenping Wang +1
Surface parameterization plays an essential role in numerous computer graphics and geometry processing applications. Traditional parameterization approaches are designed for high-q…
DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction
Yuxin Yao, Siyu Ren, Junhui Hou +3
This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose…
Dynamic 3D Point Cloud Sequences as 2D Videos
Yiming Zeng, Junhui Hou, Qijian Zhang +2
Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in b…
DDM: A Metric for Comparing 3D Shapes Using Directional Distance Fields
Siyu Ren, Junhui Hou, Xiaodong Chen +2
Qualifying the discrepancy between 3D geometric models, which could be represented with either point clouds or triangle meshes, is a pivotal issue with board applications. Existing…