This repo provides the PyTorch implementation of the work. Some code comments still need to be organized

• Ubuntu 16.04/18.04, CUDA 10.1/10.2, python >= 3.6, PyTorch >= 1.6, torchvision
• Install detectron2 from source
• sh scripts/install_deps.sh
• Compile the cpp extension for farthest points sampling (fps):

  sh core/csrc/compile.sh
  

Download the 6D pose datasets (LM, LM-O, YCB-V) from the BOP website and VOC 2012 for background images. Please also download the image_sets and test_bboxes from here (BaiduNetDisk, OneDrive, password: qjfk).

The structure of datasets folder should look like below:

# recommend using soft links (ln -sf)
datasets/
├── BOP_DATASETS
    ├──lm
    ├──lmo
    ├──ycbv
├── lm_imgn  # the OpenGL rendered images for LM, 1k/obj
├── lm_renders_blender  # the Blender rendered images for LM, 10k/obj (pvnet-rendering)
├── VOCdevkit

• lm_imgn comes from DeepIM, which can be downloaded here (BaiduNetDisk, OneDrive, password: vr0i).

• lm_renders_blender comes from pvnet-rendering, note that we do not need the fused data.

./core/gdrn_modeling/train_gdrn.sh <config_path> <gpu_ids> (other args)

Example:

./core/gdrn_modeling/train_gdrn.sh configs/gdrn/lm/a6_cPnP_lm13.py 0  # multiple gpus: 0,1,2,3
# add --resume if you want to resume from an interrupted experiment.

Our trained NMPose models can be found here (BaiduNetDisk,password:flx3).

./core/gdrn_modeling/test_gdrn.sh <config_path> <gpu_ids> <ckpt_path> (other args)

Example:

./core/gdrn_modeling/test_gdrn.sh configs/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e.py 0 output/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e/gdrn_lmo_real_pbr.pth

This work can not be finished well without the following reference, many thanks for the author's contribution: CDPN, GDR-Net