NVIDIA
NVIDIA
CenterPose - ISAAC Ros
Model
NVIDIA
NVIDIA
CenterPose - ISAAC Ros

3 pose detection model for retail objects.

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Application(s) & Domain(s):Detects the projections of 3D keypoints, estimates a 6-Degrees of Freedom (DoF) pose
Model Type:Category-Level Object Pose Estimation
Intended Users:Developers working in smart spaces, retail, and industrial applications
Output:3D Bounding-Box, Cuboid Dimensions and 6 Degrees of Freedom (DoF)
Describe how the model works:Single RGB imagedetects the projections of 3D keypoints, estimates a 6-DoF pose, and regresses the relative 3D bounding cuboid dimensions within a single RGB image.
Technical Limitations:Model should not be used in low-light, low contrast lighting conditions, with warped or motion-induced images, and with very small and very large objects. Model accuracy may vary with occlusion or truncation.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:3D Intersection-over-Union (IoU), 2D MPE (Mean Pixel Projection Error), Average Precision (AP) Azimuth Error, Average Precision (AP) Elevation Error
Potential Known Risks:This model may fail to detect projections of 3D keypoints.
Licensing:NVIDIA Open Model License

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.