FFB6D

This is the official source code for the CVPR2021 Oral work, FFB6D: A Full Flow Biderectional Fusion Network for 6D Pose Estimation. (Arxiv, Video_Bilibili, Video_YouTube)

Table of Content

• FFB6D
  • Table of Content
  • Introduction & Citation
  • Demo Video
  • Installation
  • Code Structure
  • Datasets
  • Training and evaluating
    • Training on the LineMOD Dataset
    • Evaluating on the LineMOD Dataset
    • Demo/visualizaion on the LineMOD Dataset
    • Training on the YCB-Video Dataset
    • Evaluating on the YCB-Video Dataset
    • Demo/visualization on the YCB-Video Dataset
  • Results
  • Adaptation to New Dataset
  • License

Introduction & Citation

FFB6D is a general framework for representation learning from a single RGBD image, and we applied it to the 6D pose estimation task by cascading downstream prediction headers for instance semantic segmentation and 3D keypoint voting prediction from PVN3D(Arxiv, Code, Video). At the representation learning stage of FFB6D, we build bidirectional fusion modules in the full flow of the two networks, where fusion is applied to each encoding and decoding layer. In this way, the two networks can leverage local and global complementary information from the other one to obtain better representations. Moreover, at the output representation stage, we designed a simple but effective 3D keypoints selection algorithm considering the texture and geometry information of objects, which simplifies keypoint localization for precise pose estimation.

Please cite FFB6D & PVN3D if you use this repository in your publications:

@InProceedings{He_2021_CVPR,
author = {He, Yisheng and Huang, Haibin and Fan, Haoqiang and Chen, Qifeng and Sun, Jian},
title = {FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021}
}

@InProceedings{He_2020_CVPR,
author = {He, Yisheng and Sun, Wei and Huang, Haibin and Liu, Jianran and Fan, Haoqiang and Sun, Jian},
title = {PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

Demo Video

See our demo video on YouTube or bilibili.

Installation

• Install CUDA 10.1 / 10.2

• Set up python3 environment from requirement.txt:

  pip3 install -r requirement.txt 

• Install apex:

  git clone https://github.com/NVIDIA/apex
  cd apex
  export TORCH_CUDA_ARCH_LIST="6.0;6.1;6.2;7.0;7.5"  # set the target architecture manually, suggested in issue https://github.com/NVIDIA/apex/issues/605#issuecomment-554453001
  pip3 install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
  cd ..

• Install normalSpeed, a fast and light-weight normal map estimator:

  git clone https://github.com/hfutcgncas/normalSpeed.git
  cd normalSpeed/normalSpeed
  python3 setup.py install --user
  cd ..

• Install tkinter through sudo apt install python3-tk

• Compile RandLA-Net operators:

  cd ffb6d/models/RandLA/
  sh compile_op.sh

Code Structure

Datasets

• LineMOD: Download the preprocessed LineMOD dataset from onedrive link or google drive link (refer from DenseFusion). Unzip it and link the unzipped Linemod_preprocessed/ to ffb6d/datasets/linemod/Linemod_preprocessed:

  ln -s path_to_unzipped_Linemod_preprocessed ffb6d/dataset/linemod/

  Generate rendered and fused data following raster_triangle.

• YCB-Video: Download the YCB-Video Dataset from PoseCNN. Unzip it and link the unzippedYCB_Video_Dataset to ffb6d/datasets/ycb/YCB_Video_Dataset:

  ln -s path_to_unzipped_YCB_Video_Dataset ffb6d/datasets/ycb/

Training and evaluating

Training on the LineMOD Dataset

• Train the model for the target object. Take object ape for example:

  cd ffb6d
  # commands in train_lm.sh
  n_gpu=8
  cls='ape'
  python3 -m torch.distributed.launch --nproc_per_node=$n_gpu train_lm.py --gpus=$n_gpu --cls=$cls

  The trained checkpoints are stored in train_log/linemod/checkpoints/{cls}/, train_log/linemod/checkpoints/ape/ in this example.

  A tip for saving GPU memory: you can open the mixed precision mode to save GPU memory by passing parameters opt_level=O1 to train_lm.py. The document for apex mixed precision trainnig can be found here. If you use less than 8 GPU and the batch size is less than "3x8=24", it's recommended to use mixed precision trainning and increase the mini_batch_size in common.py as large as possible.

Evaluating on the LineMOD Dataset

• Start evaluation by:

  # commands in test_lm.sh
  cls='ape'
  tst_mdl="./linemod_pretrained/FFB6D_${cls}_best.pth.tar"
  python3 -m torch.distributed.launch --nproc_per_node=1 train_lm.py --gpu '0' --cls $cls -eval_net -checkpoint $tst_mdl -test -test_pose # -debug

  You can evaluate different checkpoint by revising tst_mdl to the path of your target model.
• Pretrained model: We provide our pre-trained models for each object on onedrive, link. (The provided pretrained model here get better performance than we reported in our paper, mean ADD-0.1d 99.8). Download them and move them to their according folders. For example, move the FFB6D_ape_best.pth.tar to train_log/linemod/checkpoints/ape/. Then revise tst_mdl=train_log/linemod/checkpoints/ape/FFB6D_ape_best.path.tar for testing.

Demo/visualizaion on the LineMOD Dataset

• After training your models or downloading the pre-trained models, you can start the demo by:

  # commands in demo_lm.sh
  cls='ape'
  tst_mdl=train_log/linemod/checkpoints/${cls}/FFB6D_${cls}_best.pth.tar
  python3 -m demo -dataset linemod -checkpoint $tst_mdl -cls $cls -show

  The visualization results will be stored in train_log/linemod/eval_results/{cls}/pose_vis

Training on the YCB-Video Dataset

• Start training on the YCB-Video Dataset by:

  # commands in train_ycb.sh
  n_gpu=8  # number of gpu to use
  python3 -m torch.distributed.launch --nproc_per_node=$n_gpu train_ycb.py --gpus=$n_gpu

  The trained model checkpoints are stored in train_log/ycb/checkpoints/

  A tip for saving GPU memory: you can open the mixed precision mode to save GPU memory by passing parameters opt_level=O1 to train_ycb.py. The document for apex mixed precision trainnig can be found here. If you use less than 8 GPU and the batch size is less than "3x8=24", it's recommended to use mixed precision trainning and increase the mini_batch_size in common.py as large as possible.

Evaluating on the YCB-Video Dataset

• Start evaluating by:

  # commands in test_ycb.sh
  tst_mdl=train_log/ycb/checkpoints/FFB6D_best.pth.tar  # checkpoint to test.
  python3 -m torch.distributed.launch --nproc_per_node=1 train_ycb.py --gpu '0' -eval_net -checkpoint $tst_mdl -test -test_pose # -debug

  You can evaluate different checkpoints by revising the tst_mdl to the path of your target model.
• Pretrained model: We provide our pre-trained models on onedrive, here. Download the pre-trained model, move it to train_log/ycb/checkpoints/ and modify tst_mdl for testing.

Demo/visualization on the YCB-Video Dataset

• After training your model or downloading the pre-trained model, you can start the demo by:

  # commands in demo_ycb.sh
  tst_mdl=train_log/ycb/checkpoints/FFB6D_best.pth.tar
  python3 -m demo -checkpoint $tst_mdl -dataset ycb

  The visualization results will be stored in train_log/ycb/eval_results/pose_vis.

Results

• Evaluation result without any post refinement on the YCB-Video dataset:

  	PoseCNN		PointFusion		DenseFusion		PVN3D		Our FFF6D
  	ADDS	ADD(S)	ADDS	ADD(S)	ADDS	ADD(S)	ADDS	ADD(S)	ADDS	ADD(S)
  ALL	75.8	59.9	83.9	-	91.2	82.9	95.5	91.8	96.6	92.7

• Evaluation result on the LineMOD dataset:

  	RGB			RGB-D
  	PVNet	CDPN	DPOD	PointFusion	DenseFusion(iterative)	G2L-Net	PVN3D	FFF6D
  MEAN	86.3	89.9	95.2	73.7	94.3	98.7	99.4	99.7

• Robustness upon occlusion:

• Model parameters and speed on the LineMOD dataset (one object / frame) with one 2080Ti GPU:

  	Parameters	Network Forward	Pose Estimation	All time
  PVN3D	39.2M	170ms	20ms	190ms
  FFF6D	33.8M	57ms	18ms	75ms

Adaptation to New Dataset

• Install and generate required mesh info following DSTOOL_README.

• Modify info of your new dataset in FFB6D/ffb6d/common.py

• Write your dataset preprocess script following FFB6D/ffb6d/datasets/ycb/ycb_dataset.py. Note that you should modify or call the function that get your model info, such as 3D keypoints, center points, and radius properly.

• (Very Important!) Visualize and check if you process the data properly, eg, the projected keypoints and center point, the semantic label of each point, etc. For example, you can visualize the projected center point (red point) and selected keypoints (orange points) as follow by running python3 -m datasets.ycb.ycb_dataset.

  

• For inference, make sure that you load the 3D keypoints, center point, and radius of your objects in the object coordinate system properly in FFB6D/ffb6d/utils/pvn3d_eval_utils.py.

• Check that all setting are modified properly by using the ground truth information for evaluation. The result should be high and close to 100 if everything is correct. For example, testing ground truth on the YCB_Video dataset by passing -test_gt parameters to train_ycb.py will get results higher than 99.99:

  tst_mdl=train_log/ycb/checkpoints/FFB6D_best.pth.tar
  python3 -m torch.distributed.launch --nproc_per_node=1 train_ycb.py --gpu '0' -eval_net -checkpoint $tst_mdl -test -test_pose -test_gt
  

License

Licensed under the MIT License.