Name: J. Cappelletto
Type: User
Company: @ocean-perception @MecatronicaUSB
Bio: PhD student @ Maritime Engineering | Univ of Southampton -----------------------
Researcher @ Grupo I+D Mecatronica | Univ Simon Bolivar
Location: Southampton, UK
Blog: ocean.soton.ac.uk/
J. Cappelletto's Projects
Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
:ocean: A curated list of awesome coral research tools and resources.
AISTATS paper 'Uncertainty in Neural Networks: Approximately Bayesian Ensembling'
A simple and extensible library to create Bayesian Neural Network layers on PyTorch.
Curso EC5723: Implementación en C++ de clase básica para el uso de Algoritmos Genéticos
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
Development of CoralNet.
Course on Course: Unix Workbench. Final Project
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
🦉 Data Version Control | Git for Data & Models | ML Experiments Management
Simple C++ interface for GeoTIFF I/O using GDAL
GPT4 & LangChain Chatbot for large PDF docs
Visual odometry package based on hardware-accelerated NVIDIA Elbrus library with world class quality and performance.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Collection of assisting tools to process/consume OpLab datasets+latents into general ML pipelines
Toolbox for meshed surfaces obtained from SfM or SLAM solutions
Python scripts for Metashape (former PhotoScan)
[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning
Real-Time Dense Monocular SLAM with Neural Radiance Fields. https://arxiv.org/abs/2210.13641 + Sigma-Fusion: Probabilistic Volumetric Fusion for Dense Monocular SLAM https://arxiv.org/abs/2210.01276
Publication-ready NN-architecture schematics.
ArcGIS built-in python raster functions for deep learning to get you started fast.
A web interface to create custom vector-based visualizations on top of RAWGraphs core
A curated selection of charts provided through RAWGraphs interface
RAWGraphs core library
SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.