6DPoseAnnotator
An interactive 6 degree-of-freedom (DoF) pose annotation tool using point cloud processings.
Install / Use
/learn @sakizuki/6DPoseAnnotatorREADME
6DPoseAnnotator
An interactive 6 degree-of-freedom pose annotation tool using point cloud processings.
<img src="./data/6DoFAnnotation.gif" width="320px">Requirements
6D pose annotation with mouse and keyboard commands
Type:
$ python 6DoFPoseAnnotator.py
You can use following commands:
- Left click - Translation to the mouse pointer
- "1" - Rotation around roll axis.
- "2" - Rotation around pitch axis.
- "3" - Rotation around yaw axis.
- "i" - Pose refinement by ICP algorithm (Coarse mode).
- "f" - Pose refinement by ICP algorithm (Fine mode).
- "q" - Quit

When you type "q", a final transformation matrix, "trans.json", and a transformed point cloud, "cloud_rot.ply", are saved.
Starting from specific initial transformation
By using option "--init", you can choose initial transformation matrix to be apply.
Try:
$ python 6DoFPoseAnnotator.py --init data/trans.json
Visualization by 3D viewer
For visualizing results in 3D space, type:
$ python pv.py --input cloud_in_ds.ply cloud_rot.ply

How to get RGB and depth image?
I strongly recommend to follow pyrs repository. Images of directory "data/" were captured using that repository.
ToDo
- [x] output a total transformation matrix
- [x] add input arguments (model name, scene name)
- [x] add input argument of initial pose
- [ ] handle depth lack points
- [ ] visualize depth data of input scene
- [ ] visualize coordinate axis
Related Skills
node-connect
352.0kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
frontend-design
111.1kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
openai-whisper-api
352.0kTranscribe audio via OpenAI Audio Transcriptions API (Whisper).
qqbot-media
352.0kQQBot 富媒体收发能力。使用 <qqmedia> 标签,系统根据文件扩展名自动识别类型(图片/语音/视频/文件)。
