collaborators

5 papers

cs.CV2026

SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiability

Hanting Niu, Junkai Deng, Fei Hou +2

Multi-layer perceptrons (MLPs) are a standard tool for learning and function approximation, but they inherently produce globally smooth outputs. Consequently, they struggle to repr…

cs.CV2025

MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction

Xuhui Chen, Fei Hou, Wencheng Wang +2

Unsigned distance fields (UDFs) are widely used in 3D deep learning due to their ability to represent shapes with arbitrary topology. While prior work has largely focused on learni…

cs.CV2025

A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds Using 0-1 Integer Optimization

Zhuodong Li, Fei Hou, Wencheng Wang +2

Orienting point clouds is a fundamental problem in computer graphics and 3D vision, with applications in reconstruction, segmentation, and analysis. While significant progress has…

cs.CV2025

Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction

Cheng Xu, Fei Hou, Wencheng Wang +3

While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with…

cs.CV2025

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…