Sérgio Agostinho's Projects
PyTorch reimplementation of PPF-FoldNet
Manipulate audio with a simple and easy high level interface
Tensors and Dynamic neural networks in Python with strong GPU acceleration
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
Geometric Deep Learning Extension Library for PyTorch
PyTorch Extension Library of Optimized Scatter Operations
Python library for importing Wavefront .obj files
Rádio Zero toolset
My personal Reveal.js presentations
RPM-Net: Robust Point Matching using Learned Features (CVPR2020)
SemanticKITTI API for visualizing dataset, processing data, and evaluating results.
Config files for my GitHub profile.
My personal website
Simple and Fast Multimedia Library
This research project implements a real-time object detection and pose estimation method as described in the paper, Tekin et al. "Real-Time Seamless Single Shot 6D Object Pose Prediction", CVPR 2018. (https://arxiv.org/abs/1711.08848).
Inference code and trained networks for SSD-6D
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
:earth_africa: C++11 ply 3d mesh format importer & exporter
USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds
Open Source Visual Servoing Platform
Desktop Backup Client for Borg
A Python 3 implementation of "A Stable Algebraic Camera Pose Estimation for Minimal Configurations of 2D/3D Point and Line Correspondences." by Zhou et al. ACCV 2018