Skip to content
RobothecaBeta
Log in

OpenDroneMap (ODM)

  • Software
  • Drones and boats
  • Tool

A command-line toolkit that turns drone photos into point clouds, 3D textured models, orthophotos and elevation models. Runs on Windows, Mac and Linux.

Made by OpenDroneMap.

Source on GitHub: github.com/OpenDroneMap/ODM (opens in a new tab). Facts read at commit 77439b1 (opens in a new tab).

Licenses

Code
AGPL-3.0-only (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (AGPL-3.0-only) at commit 77439b1 (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

Copyleft: Modified source must be published, also when it runs as a service.

What it does

  • Turns 2D aerial drone images into classified point clouds, 3D textured models, georeferenced orthophotos and georeferenced digital elevation models.
  • Runs from the command line, suited to scripts and integration with other software; a desktop interface, OpenDroneMap Desktop, is also available.
  • The easiest way to run it is via Docker, placing images in an images folder and passing parameters such as --dsm.
  • Results are written to folders such as odm_meshing, odm_texturing, odm_georeferencing and odm_orthophoto.
  • Can be made accessible over a network through NodeODM.
  • Optional GPU acceleration for SIFT feature extraction, about 2x faster than CPU on a typical consumer laptop, using a dedicated GPU Docker image.

Written by Robotheca from the project's README (opens in a new tab) at commit 77439b1.

Getting started

Difficulty
Intermediate
Hardware it needs, as the project states it
Runs on Windows, Mac and Linux; Docker is the easiest route. GPU acceleration needs a CUDA-based NVIDIA card of the GTX 9xx generation or newer, with Docker's NVIDIA container support.

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
15 Sept 2026 on master
Latest release
3.6.2 (12 Aug 2026)

Checked on GitHub on 16 Oct 2026.

Links

Robots that can run it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.