search

paulpanwang / POPE

Welcome to the project repository for POPE (Promptable Pose Estimation), a state-of-the-art technique for 6-DoF pose estimation of any object in any scene using a single reference.
https://paulpanwang.github.io/POPE/
139 stars 11 forks source link

Explanation on the demo #9

Open Angus-Qi opened 10 months ago

Angus-Qi commented 10 months ago

Thanks for the contribution and releasing the code for this project, the work done is really interesting.

Regarding the visual_3dbbox.py demo, could you explain what are the prompt.txt and target.txt? I look forward to testing on other prompt and target images.

ddz16 commented 10 months ago

I have the same question. Hope for the author's reply. Thanks! @paulpanwang @zhiwenfan

ddz16 commented 9 months ago

I seem to have figured out what these two txt files mean. The 3x4 matrix in prompt.txt represents the rotation matrix (3x3) and translation (3x1) of the object relative to the camera when capturing the prompt.png image. Similarly, target.txt represents the rotation matrix and translation of the object relative to the camera when capturing the target.png image. @Angus-Qi

bsamadi commented 9 months ago

@ddz16, thank you for your response. Where can we see a definition? If we know the pose of the object in the target image, what is being calculated?