Pixano
pixano.cea.fr
- Free plan
- Windows
- macOS
- Linux
- Web
- API
- Self-hosted
What Pixano is
Pixano is an open-source tool for exploring and annotating computer vision datasets. It supports collections containing text, images, and videos, with annotation tools for boxes, polygons, pixel masks, keypoints, cuboids, classification, and tracking. Video labels can be propagated over time, while semantic search can use models such as CLIP and smart segmentation can use models such as SAM. Dataset formats such as COCO can be imported and exported, and Pixano uses Lance storage for dataset navigation. Its reusable Web Components can be assembled into custom apps. The project documents REST and Python APIs, plus Pixano Inference, a Ray Serve-based inference server with a Python client and REST API. Installation is documented through pip in a Python virtual environment or an official Docker image. The documented Python range is 3.10 or later and earlier than 3.14. Pixano is licensed under CeCILL-C and is under active development, so its API may change.
Who it suits
Pixano suits AI developers and teams working with computer vision datasets, including applications in manufacturing, security, robotics, and transportation. It is available as a web tool and through self-hosted and API options.
Good to know, and what to watch
- Supports text, image, and video datasets.
- Includes multiple annotation types and temporal propagation.
- Imports and exports formats such as COCO.
- Offers REST and Python APIs.
- The API may change during active development.
- Documented Python versions must be earlier than 3.14.
The verdict
Pixano combines dataset exploration, annotation, and model-assisted tools with documented APIs and deployment options. Its active development means users should account for possible API changes.
What the maker publishes
- 3D annotation
- The official site says users can create cuboids and match them to point clouds using geometric transformations. source
- AI features
- Pixano lists semantic search using models such as CLIP and smart segmentation using models such as SAM. source
- Annotation tools
- The official site lists bounding boxes, editable polygons, pixelwise masks, customizable labels, and temporal propagation of video annotations. source
- API
- Pixano documents a REST API and a Python API for interacting with the application and datasets. source
- Custom apps
- Pixano's reusable annotation elements are Web Components that can be assembled into a custom app. source
- Dataset formats
- It supports importing and exporting dataset formats such as COCO. source
- Dataset navigation
- Pixano uses the Lance storage format for fast dataset navigation. source
- Deployment
- The maker documents installation with pip in a Python virtual environment and official Docker releases. source
- Development status
- The project states that it is under active development and subject to API changes. source
- Founded
- 2020 source
- Headquarters
- Palaiseau, France source
- Import and export
- Pixano supports importing and exporting dataset formats such as COCO. source
- Inference integration
- Pixano Inference provides a Ray Serve based inference server with a Python client and REST API for deployed models. source
- Installation
- The project README describes installation with pip in a Python virtual environment or by running an official Docker image. source
- Intended users
- CEA-List describes Pixano as supporting AI developers and applications in areas including manufacturing, security, robotics, and transportation. source
- License
- Pixano is licensed under CeCILL-C. source
- License and maturity
- Pixano is licensed under CeCILL-C, and its README says it is under active development and subject to API changes. source
- Maker
- The product pages identify CEA List as Pixano's maker; its About page describes the LIST Institute as one of the three institutes of CEA Tech. source
- Product
- Pixano is an open-source tool for exploring and annotating computer vision datasets with AI features. source
- Purpose
- Pixano is an open-source tool for exploring and annotating computer vision datasets. source
- Requirements
- The documented Python requirement is version 3.10 or later and earlier than 3.14. source
- Security and compliance
- The pages reviewed did not state a security certification or compliance standard. source
- Semantic search
- Pixano supports semantic search using models such as CLIP. source
- Smart annotation
- It offers smart annotation components for bounding boxes, polygons, pixelwise masks, 3D bounding boxes, customizable labels, and temporal label propagation. source
Checked against the maker's pages on 30 Sept 2026.