{"id":49374559,"url":"https://github.com/grupo-avispa/depth_anything_v2_ros2","last_synced_at":"2026-04-28T01:34:24.802Z","repository":{"id":246354475,"uuid":"819280956","full_name":"grupo-avispa/depth_anything_v2_ros2","owner":"grupo-avispa","description":"ROS2 Wrapper for DepthAnything V2 model.","archived":false,"fork":false,"pushed_at":"2025-11-11T11:49:41.000Z","size":1175,"stargazers_count":130,"open_issues_count":0,"forks_count":12,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-11-11T13:19:21.182Z","etag":null,"topics":["depth","depth-anything","depth-estimation","metric-depth-estimation","monocular-depth-estimation","perception","ros","ros2"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/grupo-avispa.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-06-24T07:41:48.000Z","updated_at":"2025-11-11T11:49:45.000Z","dependencies_parsed_at":null,"dependency_job_id":"54aa4e59-71f5-45af-9d35-edff660820de","html_url":"https://github.com/grupo-avispa/depth_anything_v2_ros2","commit_stats":null,"previous_names":["grupo-avispa/depth_anything_v2_ros2"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/grupo-avispa/depth_anything_v2_ros2","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grupo-avispa%2Fdepth_anything_v2_ros2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grupo-avispa%2Fdepth_anything_v2_ros2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grupo-avispa%2Fdepth_anything_v2_ros2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grupo-avispa%2Fdepth_anything_v2_ros2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/grupo-avispa","download_url":"https://codeload.github.com/grupo-avispa/depth_anything_v2_ros2/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grupo-avispa%2Fdepth_anything_v2_ros2/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32362781,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-27T20:07:02.737Z","status":"ssl_error","status_checked_at":"2026-04-27T20:07:00.910Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["depth","depth-anything","depth-estimation","metric-depth-estimation","monocular-depth-estimation","perception","ros","ros2"],"created_at":"2026-04-28T01:34:24.447Z","updated_at":"2026-04-28T01:34:24.791Z","avatar_url":"https://github.com/grupo-avispa.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# depth_anything_v2_ros2\r\n![ROS2](https://img.shields.io/badge/ros2-jazzy-blue?logo=ros\u0026logoColor=white)\r\n[![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](https://opensource.org/licenses/Apache-2.0)\r\n[![Build](https://github.com/grupo-avispa/depth_anything_v2_ros2/actions/workflows/build.yml/badge.svg?branch=main)](https://github.com/grupo-avispa/depth_anything_v2_ros2/actions/workflows/build.yml)\r\n\r\n## Overview\r\nThis package is a ROS2 wrapper for the [depth_anything_v2](https://github.com/DepthAnything/Depth-Anything-V2) library. It provides a ROS2 node that subscribes to a camera topic and publishes the depth map of the scene.\r\n\r\n |        *RGB*        |         *Depth*         |\r\n | :-----------------: | :---------------------: |\r\n | ![RGB](doc/raw.png) | ![Depth](doc/depth.png) |\r\n\r\n\r\nThe depth_anything_v2_ros2 package has been tested under [ROS2] jazzy on [Ubuntu] 22.04. This is research code, expect that it changes often and any fitness for a particular purpose is disclaimed.\r\n\r\n## Installation\r\n### Building from Source\r\n\r\n#### Dependencies\r\n\r\n- [Robot Operating System (ROS) 2](https://docs.ros.org/en/jazzy/) (middleware for robotics),\r\n- [depth_anything_v2](https://github.com/DepthAnything/Depth-Anything-V2) (library for depth estimation),\r\n- [torch](https://pytorch.org/) (deep learning framework)\r\n\r\n#### Building\r\n\r\nTo build from source, clone the latest version from the main repository into your colcon workspace and install the python dependencies by running the following commands:\r\n```bash\r\ncd colcon_workspace/src\r\ngit clone --recurse-submodules https://github.com/grupo-avispa/depth_anything_v2_ros2.git -b main\r\npip3 install -r requirements.txt\r\n```\r\nBefore building, make sure to download the depth_anything_v2 model weights and place them in the `models` directory. You can download them [here](https://huggingface.co/depth-anything).\r\n\r\nThen, install the ROS2 dependencies using rosdep and build the package using:\r\n```bash\r\ncd colcon_workspace\r\nrosdep install -i --from-path src --rosdistro jazzy -y\r\ncolcon build --symlink-install\r\n```\r\n\r\n## Usage\r\n\r\nWith some RGB image source running, run the depth_anything_v2_ros2 node with:\r\n```bash\r\nros2 launch depth_anything_v2_ros2 default.launch.py\r\n```\r\n\r\n## Nodes\r\n\r\n### depth_anything\r\n\r\nThis node subscribes to a camera topic and publishes the depth map of the scene.\r\n\r\n#### Subscribed Topics\r\n\r\n* **`camera/color/image_raw`** ([sensor_msgs/Image])\r\n\r\n\tThe RGB image topic.\r\n\r\n#### Published Topics\r\n\r\n* **`depth`** ([sensor_msgs/Image])\r\n\r\n\tThe depth map estimated of the scene.\r\n\r\n#### Parameters\r\n\r\n* **`image_topic`** (string, default: \"camera/color/image_raw\")\r\n\r\n\tTopic where the image will be subscribed.\r\n\r\n* **`depth_image_topic`** (string, default: \"depth\")\r\n\r\n\tTopic where the raw depth image will be published.\r\n\r\n* **`device`** (string, default: \"cuda:0\")\r\n\r\n\tDevice to use for the inference (`cpu` or `cuda`).\r\n\r\n* **`model_file`** (string, default: \"depth_anything_v2_vits.pth\")\r\n\r\n\t Path to the model, located in the `models` directory.\r\n\r\n* **`encoder`** (string, default: \"vits\")\r\n\r\n\tEncoder to use for the inference (`vits`, `vitb` or `vitl`).\r\n\r\n\r\n[Ubuntu]: https://ubuntu.com/\r\n[ROS2]: https://docs.ros.org/en/jazzy/\r\n[sensor_msgs/Image]: https://docs.ros2.org/jazzy/api/sensor_msgs/msg/Image.html\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrupo-avispa%2Fdepth_anything_v2_ros2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgrupo-avispa%2Fdepth_anything_v2_ros2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrupo-avispa%2Fdepth_anything_v2_ros2/lists"}