Focus on prompting and generating

We write your reusable computer vision tools. 💜

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Panel: The powerful data exploration & web app framework for Python

Python package for the evaluation of odometry and SLAM

[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

ECCV2020 paper "Whole-Body Human Pose Estimation in the Wild"

Efficient facial landmark detector

A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.

CellViT: Vision Transformers for Precise Cell Segmentation and Classification

Unofficial Gato: A Generalist Agent

A TensorFlow implementation of HRNet for facial landmark detection.

An oriented bounding boxes implement of YOLOv3 with SEnet , Deformable Convolution and rotated NMS written in CUDA

Robot localization using AprilTag markers.

ROS2 package to follow a person

🔥🔥 Deep Learning Head Pose Estimation using PyTorch.

Perception for human robot handover

Gesture Recognition Algorithm integrated for ROS Melodic