gurpreetshanky / CenterPose

Single-stage Keypoint-based Category-level Object Pose Estimation from an RGB Image

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool



This repository is the official implementation of the paper "Single-stage Keypoint-based Category-level Object Pose Estimation from an RGB Image" by Lin et al. (full citation below). In this work, we propose a single-stage, keypoint-based approach for category-level object pose estimation, which operates on unknown object instances within a known category using a single RGB image input. The proposed network performs 2D object detection, detects 2D keypoints, estimates 6-DoF pose, and regresses relative 3D bounding cuboid dimensions. These quantities are estimated in a sequential fashion, leveraging the recent idea of convGRU for propagating information from easier tasks to those that are more difficult. We favor simplicity in our design choices: generic cuboid vertex coordinates, a single-stage network, and monocular RGB input. We conduct extensive experiments on the challenging Objectron benchmark of real images, outperforming state-of-the-art methods for 3D IoU metric (27.6% higher than the single-stage approach of MobilePose and 7.1% higher than the related two-stage approach). The algorithm runs at 15 fps on an NVIDIA GTX 1080Ti GPU.


The code was tested on Ubuntu 16.04, with Anaconda Python 3.6 and PyTorch 1.1.0. Higher versions should be possible with some accuracy difference. NVIDIA GPUs are needed for both training and testing.


For hardware-accelerated ROS2 inference support, please visit Isaac ROS CenterPose which has been tested with ROS2 Foxy on Jetson AGX Xavier/JetPack 4.6 and on x86/Ubuntu 20.04 with RTX3060i.

  1. Clone this repo:

    git clone $CenterPose_ROOT
  2. Create an Anaconda environment or create your own virtual environment

    conda create -n CenterPose python=3.6
    conda activate CenterPose
    pip install -r requirements.txt
    conda install -c conda-forge eigenpy
  3. Compile the deformable convolutional layer

    git submodule init
    git submodule update
    cd $CenterPose_ROOT/src/lib/models/networks/DCNv2

    [Optional] If you want to use a higher version of PyTorch, you need to download the latest version of DCNv2 and compile the library.

    git submodule set-url src/lib/models/networks/DCNv2
    git submodule sync
    git submodule update --init --recursive --remote
    cd $CenterPose_ROOT/src/lib/models/networks/DCNv2
  4. Download our pre-trained models for CenterPose and move all the .pth files to $CenterPose_ROOT/models/CenterPose/. We currently provide models for 9 categories: bike, book, bottle, camera, cereal_box, chair, cup, laptop, and shoe.

  5. Prepare training/testing data

    We save all the training/testing data under $CenterPose_ROOT/data/.

    For the Objectron dataset, we created our own data pre-processor to extract the data for training/testing. Refer to the data directory for more details.


We provide supporting demos for image, videos, webcam, and image folders. See $CenterPose_ROOT/images/CenterPose

For category-level 6-DoF object estimation on images/video/image folders, run:

cd $CenterPose_ROOT/src
python --demo /path/to/image/or/folder/or/video --arch dlav1_34 --load_model ../path/to/model

You can also enable --debug 4 to save all the intermediate and final outputs.

For the webcam demo (You may want to specify the camera intrinsics via --cam_intrinsic), run

cd $CenterPose_ROOT/src
python --demo webcam --arch dlav1_34 --load_model ../path/to/model


We follow the approach of CenterNet for training the DLA network, reducing the learning rate by 10x after epoch 90 and 120, and stopping after 140 epochs.

For debug purposes, you can put all the local training params in the $CenterPose_ROOT/src/ script. You can also use the command line instead. More options are in $CenterPose_ROOT/src/lib/

To start a new training job, simply do the following, which will use default parameter settings:

cd $CenterPose_ROOT/src

The result will be saved in $CenterPose_ROOT/exp/object_pose/$dataset_$category_$arch_$time ,e.g., objectron_bike_dlav1_34_2021-02-27-15-33

You could then use tensorboard to visualize the training process via

cd $path/to/folder
tensorboard --logdir=logs --host=XX.XX.XX.XX


We evaluate our method on the Objectron dataset, please refer to the objectron_eval directory for more details.


Please cite grasp_primitiveShape if you use this repository in your publications:

  title={Single-stage Keypoint-based Category-level Object Pose Estimation from an RGB Image},
  author={Lin, Yunzhi and Tremblay, Jonathan and Tyree, Stephen and Vela, Patricio A and Birchfield, Stan},
  journal={arXiv preprint arXiv:2109.06161},


CenterPose is licensed under the NVIDIA Source Code License - Non-commercial.

ezoic increase your site revenue


Single-stage Keypoint-based Category-level Object Pose Estimation from an RGB Image



Language:Python 86.2%Language:C++ 6.9%Language:Cuda 5.8%Language:C 1.2%Language:Shell 0.0%