5 citations · 8 across the 11 of their papers we have counts for
13 papers
Volume Rendering with Metric--Phase Fields for Thin Structures and Sign-Ambiguous Geometry
Junkai Deng, Jiayi Kong, Xuhui Chen +5
Neural implicit surface methods that couple volume rendering with signed distance functions (SDFs), such as VolSDF and NeuS, achieve high-quality multi-view reconstruction for wate…
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…
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…
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…
Voronoi-Assisted Optimization for Diffusing Unsigned Distance Fields from Unoriented Points
Jiayi Kong, Chen Zong, Junkai Deng +6
Unsigned Distance Fields (UDFs) provide a flexible representation for 3D shapes with arbitrary topology, including open and closed surfaces, orientable and non-orientable geometrie…
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with -NeuS
Haoran Zhang, Junkai Deng, Xuhui Chen +5
Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. R…
Quasi-Medial Distance Field (Q-MDF): A Robust Method for Approximating and Discretizing Neural Medial Axes
Jiayi Kong, Chen Zong, Jun Luo +5
The medial axis, a lower-dimensional descriptor that captures the extrinsic structure of a shape, plays an important role in digital geometry processing. Despite its importance, co…
A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions
Jiangbei Hu, Yanggeng Li, Fei Hou +5
Unsigned distance fields (UDFs) provide a versatile framework for representing a diverse array of 3D shapes, encompassing both watertight and non-watertight geometries. Traditional…
GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lighting
Jiaze Li, Zhengyu Wen, Luo Zhang +4
The 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi-view images, enabling real-time rendering. While point-based rasteriza…
Diffusing Winding Gradients (DWG): A Parallel and Scalable Method for 3D Reconstruction from Unoriented Point Clouds
Weizhou Liu, Jiaze Li, Xuhui Chen +6
This paper presents a new method, Diffusing Winding Gradients (DWG), for reconstructing watertight 3D surfaces from unoriented point clouds. Our method exploits the alignment betwe…
Topology-Aware Latent Diffusion for 3D Shape Generation
Jiangbei Hu, Ben Fei, Baixin Xu +6
We introduce a new generative model that combines latent diffusion with persistent homology to create 3D shapes with high diversity, with a special emphasis on their topological ch…
Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering
Baixin Xu, Jiangbei Hu, Fei Hou +4
The advancements in neural rendering have increased the need for techniques that enable intuitive editing of 3D objects represented as neural implicit surfaces. This paper introduc…
Hierarchical Vectorization for Portrait Images
Qian Fu, Linlin Liu, Fei Hou +1
Aiming at developing intuitive and easy-to-use portrait editing tools, we propose a novel vectorization method that can automatically convert raster images into a 3-tier hierarchic…