[ROBOVIS 2025] Official Implementation: Automating 3D Dataset Generation with Neural Radiance Fields

We write your reusable computer vision tools. 💜

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

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

Gesture Recognition Algorithm integrated for ROS Melodic

Additional required info for the ICSR 23 paper

CellViT: Vision Transformers for Precise Cell Segmentation and Classification

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.

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

Focus on prompting and generating

A ROS package for detecting and locating 3D objects

ROS2 package to follow a person

Robot localization using AprilTag markers.

NVIDIA Deep learning Dataset Synthesizer (NDDS)

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

Jekyll theme for research project websites 🧫

Efficient facial landmark detector

Unofficial Gato: A Generalist Agent

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

Perception for human robot handover

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

A TensorFlow implementation of HRNet for facial landmark detection.

Latex code for making neural networks diagrams

Best Practices, code samples, and documentation for Computer Vision.

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

Python package for the evaluation of odometry and SLAM

pcl examples

A simple tar implementation in C

Official Source Repo for DeepOnion - Anonymous Cryptocurrency on TOR

DynaSLAM is a SLAM system robust in dynamic environments for monocular, stereo and RGB-D setups