Perception Python Packages

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

mediapipe-nightly

Cross-platform, customizable ML solutions for live and streaming media.

mediapipe-model-maker

Cross-platform, customizable ML solutions for live and streaming media.

kiss-slam

A LiDAR SLAM system that just works

truckscenes-devkit

Development Kit for the MAN TruckScenes Dataset

trio-retina

Model-agnostic computer-vision pipeline: turn any detector (YOLO, VLM, Grounding DINO) into structured tracking events — zone intrusion, line-crossing, dwell, counting — over video or RTSP. The state layer for world models.

ros2-unbag

A ROS 2 tool for exporting bags to human readable files. Supports pluggable export routines to handle any message type.

slip

a Simple Library for Image Processing

perceive

Compact, ref-stable, reachability-filtered perception for AI browser agents

tagmaps

Tag Clustering for Tag Maps

robot-lidar-fusion

The open-source control stack for autonomous robots with LiDAR-camera sensor fusion.

pipeless-ai-tf-models

An open-source computer vision framework to build and deploy apps in minutes

perception-model

Perception Model

odak

Scientific computing library for optics, computer graphics and visual perception.

fnvision

Biologically-motivated foveated vision encoder for autonomous agents and robotics. Two coupled foveal centers (F1/F2) with Gaussian resolution fields. Zoom via a single parameter: F-center convergence. No transformers, no distortion. Live calibration tool included.

loggabor

A python implementation for a LogGabor filtering and pyramid representation

pipeless-ai

An open-source computer vision framework to create and deploy computer vision applications that scale in minutes

motionclouds

Synthesizing moving textures with parameterized features

pipeless-ai-cli

An open-source computer vision framework to create and deploy computer vision applications that scale in minutes

sorceress

Python package for creating optical illusions

openemma

OpenEMMA is an open-source implementation of Waymo's End-to-End Multimodal Model for Autonomous Driving (EMMA).

pyllusion

A Parametric Framework to Generate Visual Illusions using Python

oviz

Oviz: A powerful visualization tool for all your data. See images, point clouds, and more. Your go-to choice for effortless visualization!

telluride-decoding

Telluride Decoding Toolbox