Stephan Sturges

WALDO. Whereabouts Ascertainment for Low-lying Detectable Objects. The SOTA in FOSS AI for drones!

NANO. Neural Autonomous Navigation Observer is a set of very small DNNs for drones to detect a few simple objects

GPTflix. Simple Pinecone + OpenAI framework to do RAG on movie reviews (or anything else)

OpenLander. free-to-use landing-zone detection for UAV using DNNs for object segmentation! Also works for drone delivery 😁

Tator. a *fast* image-data annotator leveraging foundation models for automation

MAVERICC. Machine Assisted Visual Extraction, Reconnaissance & Intelligence for Cosmic Captures

yolobbox2polygon. this is a dataset converter that takes YOLO bbox data and makes polygons using SAM-HQ!

HOT. Human Object Tracking (in thermal imagery)

UNIDRONE. one AI model for drone-based detection to rule them all 😄

BAD. Bipedal Activity Detector is a very small trained short-range AI segmentation network for detecting people

yolov8_peopleonly. this is a trained yolov8n network that only detects people, at "eye-height", trained in a super basic way on COCO

UFO. lightweight embeddable DNNs for spotting shaheds

Open3D-PointNet2-Semantic3D_fork. Python

vectorized_wikipedia_complete. This is a complete dump of English language Wikipedia vectorized with SBERT all-mpnet-base-v2

StereoVision. Library and utilities for 3d reconstruction from stereo cameras.

mega.pytorch. Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020

darknet. YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

autodistill. Images to inference with no labeling (use foundation models to train supervised models)

iq_image_generator. Aerospace style image generator designed for mavlink based vehicles

SAM-CD-test. Pytorch code of the SAM-CD

wikipedia_converter. Python

calib_example. simple implementation of calibration with a dot chart

lstm-object-detection. Object Detection using LSTM-SSD

blog. 🚀⚡️ Blazing fast blog built with Gatsby and the Cosmic Headless CMS 🔥

Self-Driving-Anki-Vector. Python

spatter. overlay augmentations on training data

kiss-icp-test. KISS-ICP: In Defense of Point-to-Point ICP – Simple, Accurate, and Robust Registration If Done in the Right Way https://arxiv.org/pdf/2209.15397.pdf

m5paper-micropythonw. Ambient display using M5Paper that display data from a http endpoint

DeepSDF. Learning Continuous Signed Distance Functions for Shape Representation

DeepHuman. Code for our ICCV paper "DeepHuman: 3D Human Reconstruction from a Single Image"

HumanNeRF_test. HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs(Published in CVPR2022)

depthai-TopFormer-Semantic-Segmentation. Python scripts performing on devive semantic segmentation using the TopFormer model in depthai.

RealSense. Realsense camera stitching developent

smplify-x. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

labelbox_pixelmask_downloader. Python

depthai-UVC-playground. Making a webcam app for depthai cameras based off the default demo.py

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily search and find personal or work documents by asking questions in everyday language.

opencv-python. This repository generates precompiled opencv-python, opencv-python-headless, opencv-contrib-python and opencv-contrib-python-headless packages.

IPNet. Repo for "Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction, ECCV'20(Oral)""

KinectAzureDKProgramming. Samples about Kinect Azure DK programming

AnyLoc. Official Code Repository for AnyLoc

segment-lidar-tests. Python package for segmenting aerial LiDAR data using Segment-Anything Model (SAM) from Meta AI.

M5PaperW. M5Paper project for funsies

K4aGrabber. Kinect Azure DK Grabber of PCL (Point Cloud Library).

pointnet_own. Personal implementation of PointNet in TF 2.0

depthai-slam-test. SLAM using OAKs (python)

tex2shape. This repository contains code corresponding to the paper "Tex2Shape: Detailed Full Human Body Geometry from a Single Image"

teslausb. Steps and scripts for turning a Raspberry Pi into a useful USB drive for a Tesla

ARDrone---ChArUco---Detection-. This is 2018 summer project at Gatech. Supervised by Professor Vela and Yipu Zhao.

smplx. SMPL-X

gpt-oss-20b_GPS_distance_understanding_finetune. A little project to figure out whether we can tech a small LLM to have an intuitive understanding of distances using a synthetic data set and some simple fine-tuning.

shadow_augmentor. Python