keeganhk

Ph.D. at City University of Hong Kong.

Hong Kong

Pinned Repositories

Flattening-Net
Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis
Language:C++68 10 311
keeganhk.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Language:JavaScript1 0 00
NeuroGF
NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
Language:C++56 11 010
PointMCD
PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition
Language:C++48 10 310
PointVST
Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation
Language:C++30 2 00
RegGeoNet
RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds
Language:C++44 4 11
OptCuts
OptCuts, a new parameterization algorithm, jointly optimizes arbitrary embeddings for seam quality and distortion. OptCuts requires no parameter tuning; automatically generating mappings that minimize seam-lengths while satisfying user-requested distortion bounds.
Language:C++279 21 2147

keeganhk/Flattening-Net
Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis
Language:C++68 10 311
keeganhk/NeuroGF
NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
Language:C++56 11 010
keeganhk/PointMCD
PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition
Language:C++48 10 310
keeganhk/RegGeoNet
RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds
Language:C++44 4 11
keeganhk/PointVST
Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation
Language:C++30 2 00
keeganhk/FlattenAnything
Flatten Anything: Unsupervised Neural Surface Parameterization
Language:C++5
keeganhk/keeganhk.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Language:JavaScript1 0 00