-
University of Bonn
- https://paulroetzer.github.io
Stars
Implementation of Efficient Deformable Shape Correspondence via Kernel Matching (https://arxiv.org/abs/1707.08991).
Library to solve (multi-)graph matching problems.
CVPR 2025, EchoMatch: Partial-to-Partial Shape Matching via Correspondence Reflection
MICCAI24: A Universal and Flexible Framework for Unsupervised Statistical Shape Model Learning
Official repository for the SGP 2025 paper: "High-Resolution 3D Shape Matching with Global Optimality and Geometric Consistency" by Nafie El Amrani, Paul Roetzer and Florian Bernard (University of …
CVPR 2024, Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching
A library of geometry processing tools for computer graphics
A Jekyll version of the "Massively" theme by HTML5 UP.
PIPS-IPM++ - a massively parallel interior point method for primal-dual block angular Linear Programms
Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.
Optimum cycle mean algorithms: Efficient implementations as used in my research papers.
Rotation-Invariant Transformer for Point Cloud Matching
Refine high-quality datasets and visual AI models
This repository implements the remeshing algorithm presented in ReMatching: Low-Resolution Representations for Scalable Shape Correspondence.
PyTorch common framework to accelerate network implementation, training and validation
Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features [CVPR 2024]
Stanford LaTeX poster template
Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis
CVPR 2024, Partial-to-Partial Shape Matching with Geometric Consistency
Implementation of the paper "Surface Map Homology Inference"
Demo code for the paper "Discrete Optimization for Shape Matching"
Accompanying code for "An Elastic Basis for Spectral Shape Correspondence"
Surface Simplification using Intrinsic Error Metrics