CenterPose
Single-Stage Keypoint-based Category-level Object Pose Estimation from an RGB Image (ICRA 2022) (by NVlabs)
PoseCNN-PyTorch
PyTorch implementation of the PoseCNN framework (by NVlabs)
| CenterPose | PoseCNN-PyTorch | |
|---|---|---|
| 2 | 2 | |
| 251 | 168 | |
| 0.0% | 0.0% | |
| 0.0 | 10.0 | |
| over 1 year ago | about 2 years ago | |
| Python | C | |
| GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
CenterPose
Posts with mentions or reviews of CenterPose.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-10-07.
-
6D object pose estimation by known 3d model
I've been doing some research in this area and there are a few deep learning solutions to this problem. For example, NVIDIA's Deep Object Pose Estimation will estimate the 6DOF pose of a known object. But you'll have to train the network if you want to detect a new object. PoseCNN, which someone else mentioned, does a similar thing. CenterPose is more interesting, as it can estimate then pose of an object from a known category; e.g. sneakers, or laptops, rather that one specific object (as DOPE and PoseCNN do).
-
Unknown object tracking state of the art?
If you want the poses of unknown objects within known categories (e.g. "shoe" or "laptop") there are several deep learning approaches. Here's one I'm currently experimenting with: https://github.com/NVlabs/CenterPose
PoseCNN-PyTorch
Posts with mentions or reviews of PoseCNN-PyTorch.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-10-07.
-
Estimating pose of a rigid object
I'm working on estimating the 6D pose of a rigid object. I see some older work that seems related such as PoseCNN https://github.com/NVlabs/PoseCNN-PyTorch however this uses older network architectures (VGG).
-
6D object pose estimation by known 3d model
I've been doing some research in this area and there are a few deep learning solutions to this problem. For example, NVIDIA's Deep Object Pose Estimation will estimate the 6DOF pose of a known object. But you'll have to train the network if you want to detect a new object. PoseCNN, which someone else mentioned, does a similar thing. CenterPose is more interesting, as it can estimate then pose of an object from a known category; e.g. sneakers, or laptops, rather that one specific object (as DOPE and PoseCNN do).
What are some alternatives?
When comparing CenterPose and PoseCNN-PyTorch you can also consider the following projects:
iNeRF-public
Deep_Object_Pose - Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
Hierarchical-Localization - Visual localization made easy with hloc
GraphCut - Graph cut image segmentation with custom GUI.