Paul-Edouard Sarlin
sarlinpe
Researcher at Google. 3D Computer Vision + Machine Learning. Previously PhD @ ETH Zurich @cvg, intern at Google, Meta Reality Labs, Microsoft, Magic Leap.
Languages
Loading contributions...
Top Repositories
A clean TensorFlow implementation of Concrete Dropout
Embedded hardware accelerator of multilayer perceptrons for lightweight machine learning
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
Public release of the Image Matching Benchmark: https://vision.uvic.ca/image-matching-challenge
Optimal Transport Aggregation for Visual Place Recognition
GL3D (Geometric Learning with 3D Reconstruction): a large-scale database created for 3D reconstruction and geometry-related learning problems
Repositories
41Embedded hardware accelerator of multilayer perceptrons for lightweight machine learning
Generate stubs for python modules
Optimal Transport Aggregation for Visual Place Recognition
A realistic ROS/Gazebo simulation of Robopoly's PRisme robotic platform with improved hardware compatibility
Public release of the Image Matching Benchmark: https://vision.uvic.ca/image-matching-challenge
A collaboration friendly studio for NeRFs
A clean TensorFlow implementation of Concrete Dropout
Minimal solvers for calibrated camera pose estimation
Flax is a neural network library for JAX that is designed for flexibility.
From Coarse to Fine: Robust Hierarchical Localization at Large Scale with HF-Net (https://arxiv.org/abs/1812.03506)
Seamless operability between C++11 and Python
projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data
A large scale non-linear optimization library
Comparative Evaluation of Hand-Crafted and Learned Local Features
C++ Library Manager for Windows, Linux, and MacOS
Efficient neural feature detector and descriptor
Vim plugins and configuration files
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
🇫🇷 Oh My Tmux! Pretty & versatile tmux configuration made with ❤️ (imho the best tmux configuration that just works)
COLMAP - Structure-from-Motion and Multi-View Stereo
No description provided.
Catkin wrapper for a Bazel-free build of Tensorflow
The public CGAL repository, see the README below
Python bindings for COLMAP estimators
Recognizing individual 2D joint locations in images
Provide mapping and localization pipelines based on kapture format
GL3D (Geometric Learning with 3D Reconstruction): a large-scale database created for 3D reconstruction and geometry-related learning problems
Multi-View Optimization of Local Feature Geometry
:stew: Let's make it easier for people to cook! Third place at Ideasinc's Startathon 2016.
A Turtlebot navigation stack for the mapping of simplified environments