shin-ka

rosa

ROSA is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.

smol-Diffusion

Implemented DDPM Diffusion model from scratch. Trained a attention-based U-Net

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

smalldiffusion

Simple and readable code for training and sampling from diffusion models

SOccDPT

AAIML 2024: 3D Semantic Occupancy from Dense Prediction Transformers trained under memory constraints

depth_anything_v2_ros2

ROS2 Wrapper for DepthAnything V2 model.

PythonRobotics

Python sample codes for robotics algorithms.

dust3r

DUSt3R: Geometric 3D Vision Made Easy

LightGlue

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

TEASER-plusplus

A fast and robust point cloud registration library

flowsam

Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi Xie, Andrew Zisserman

ROS-LLM

ROS-LLM is a framework designed for embodied intelligence applications in ROS. It allows natural language interactions and leverages Large Language Models (LLMs) for decision-making and robot control. With an easy configuration process, this framework allows for swift integration, enabling your robot to operate with it in as little as ten minutes.

HelMoRo-software

The repository collects the main software for HelMoRo

Clio

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

open-interpreter

A natural language interface for computers

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

elevation_mapping_cupy

Elevation Mapping on GPU.

ISSA

Official implementation of "Intra-Source Style Augmentation for Improved Domain Generalization" (WACV 2023 & IJCV)

Object-Detection-on-Thermal-Images

Robust Object Classification of Occluded Objects in Forward Looking Infrared (FLIR) Cameras

salaryconverter

Equivalent salary converter using PPP

supervision

We write your reusable computer vision tools. 💜

Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

owl-vit-object-detection

object detection based on owl-vit

autolitt

Light up!

vo-survey

Visual Odometry and SLAM survey for ROS and ROS2

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

idisc

iDisc: Internal Discretization for Monocular Depth Estimation [CVPR 2023]

rosgpt

ROSGPT is a pioneering approach that combines the power of ChatGPT and ROS (Robot Operating System) to redefine human-robot interaction. By leveraging large language models like ChatGPT, ROSGPT enables the conversion of unstructured human language into actionable robotic commands. T

SoccerKicks

A dataset that provides 3D guide movements for dead ball kicks (penalty and foul) obtained from reference videos suitable for use in the robotics soccer domain.