[ICCV' 21] "Unsupervised Point Cloud Pre-training via Occlusion Completion"

Overview

OcCo: Unsupervised Point Cloud Pre-training via Occlusion Completion

This repository is the official implementation of paper: "Unsupervised Point Cloud Pre-training via Occlusion Completion"

[Paper] [Project Page]

Intro

image

In this work, we train a completion model that learns how to reconstruct the occluded points, given the partial observations. In this way, our method learns a pre-trained encoder that can identify the visual constraints inherently embedded in real-world point clouds.

We call our method Occlusion Completion (OcCo). We demonstrate that OcCo learns representations that: improve generalization on downstream tasks over prior pre-training methods, transfer to different datasets, reduce training time, and improve labeled sample efficiency.

Citation

Our paper is preprinted on arxiv:

@inproceedings{OcCo,
	title = {Unsupervised Point Cloud Pre-Training via Occlusion Completion},
	author = {Hanchen Wang and Qi Liu and Xiangyu Yue and Joan Lasenby and Matthew J. Kusner},
	year = 2021,
	booktitle = {International Conference on Computer Vision, ICCV}
}

Usage

We provide codes in both PyTorch (1.3): OcCo_Torch and TensorFlow (1.13-1.15): OcCo_TF. We also provide with docker configuration docker. Our recommended development environment PyTorch + docker, the following descriptions are based on OcCo_Torch, we refer the readme in the OcCo_TF for the details of TensorFlow implementation.

1) Prerequisite

Docker

In the docker folder, we provide the build, configuration and launch scripts:

docker
| - Dockerfile_Torch  # configuration
| - build_docker_torch.sh  # scripts for building up from the docker images
| - launch_docker_torch.sh  # launch from the built image
| - .dockerignore  # ignore the log and data folder while building up 

which can be automatically set up as following:

# build up from docker images
cd OcCo_Torch/docker
sh build_docker_torch.sh

# launch the docker image, conduct completion/classification/segmentation experiments
cd OcCo_Torch/docker
sh launch_docker_torch.sh
Non-Docker Setup

Just go with pip install -r Requirements_Torch.txt with the PyTorch 1.3.0, CUDA 10.1, CUDNN 7 (otherwise you may encounter errors while building the C++ extension chamfer_distance for calculating the Chamfer Distance), my development environment besides docker is Ubuntu 16.04.6 LTS, gcc/g++ 5.4.0, cuda10.1, CUDNN 7.

2) Pre-Training via Occlusion Completion (OcCo)

Data Usage:

For the details in the data setup, please see data/readme.md.

Training Scripts:

We unify the training of all three models (PointNet, PCN and DGCNN) in train_completion.py as well as the bash templates, see bash_template/train_completion_template.sh for details:

#!/usr/bin/env bash

cd ../

# train pointnet-occo model on ModelNet, from scratch
python train_completion.py \
	--gpu 0,1 \
	--dataset modelnet \
	--model pointnet_occo \
	--log_dir modelnet_pointnet_vanilla ;

# train dgcnn-occo model on ShapeNet, from scratch
python train_completion.py \
	--gpu 0,1 \
	--batch_size 16 \
	--dataset shapenet \
	--model dgcnn_occo \
	--log_dir shapenet_dgcnn_vanilla ;
Pre-Trained Weights

We will provide the OcCo pre-trained models for all the three models here, you can use them for visualization of completing self-occluded point cloud, fine tuning on classification, scene semantic and object part segmentation tasks.

3) Sanity Check on Pre-Training

We use single channel values as well as the t-SNE for dimensionality reduction to visualize the learned object embeddings on objects from the ShapeNet10, while the encoders are pre-trained on the ModelNet40 dataset, see utils/TSNE_Visu.py for details.

We also train a Support Vector Machine (SVM) based on the learned embeddings object recognition. It is in train_svm.py. We also provide the bash template for this, see bash_template/train_svm_template.sh for details:

#!/usr/bin/env bash

cd ../

# fit a simple linear SVM on ModelNet40 with OcCo PCN
python train_svm.py \
	--gpu 0 \
	--model pcn_util \
	--dataset modelnet40 \
	--restore_path log/completion/modelnet_pcn_vanilla/checkpoints/best_model.pth ;

# grid search the best svm parameters with rbf kernel on ScanObjectNN(OBJ_BG) with OcCo DGCNN
python train_svm.py \
	--gpu 0 \
	--grid_search \
	--batch_size 8 \
	--model dgcnn_util \
	--dataset scanobjectnn \
	--bn \
	--restore_path log/completion/modelnet_dgcnn_vanilla/checkpoints/best_model.pth ;

4) Fine Tuning Task - Classification

Data Usage:

For the details in the data setup, please see data/readme.md.

Training/Testing Scripts:

We unify the training and testing of all three models (PointNet, PCN and DGCNN) in train_cls.py. We also provide the bash template for training each models from scratch, JigSaw/OcCo pre-trained checkpoints, see bash_template/train_cls_template.sh for details:

#!/usr/bin/env bash

cd ../

# training pointnet on ModelNet40, from scratch
python train_cls.py \
	--gpu 0 \
	--model pointnet_cls \
	--dataset modelnet40 \
	--log_dir modelnet40_pointnet_scratch ;

# fine tuning pcn on ScanNet10, using jigsaw pre-trained checkpoints
python train_cls.py \
	--gpu 0 \
	--model pcn_cls \
	--dataset scannet10 \
	--log_dir scannet10_pcn_jigsaw \
	--restore \
	--restore_path log/completion/modelnet_pcn_vanilla/checkpoints/best_model.pth ;

# fine tuning dgcnn on ScanObjectNN(OBJ_BG), using jigsaw pre-trained checkpoints
python train_cls.py \
	--gpu 0,1 \
	--epoch 250 \
	--use_sgd \
	--scheduler cos \
	--model dgcnn_cls \
	--dataset scanobjectnn \
	--bn \
	--log_dir scanobjectnn_dgcnn_occo \
	--restore \
	--restore_path log/completion/modelnet_dgcnn_vanilla/checkpoints/best_model.pth ;

# test pointnet on ModelNet40 from pre-trained checkpoints
python train_cls.py \
	--gpu 1 \
	--mode test \
	--model pointnet_cls \
	--dataset modelnet40 \
	--log_dir modelnet40_pointnet_scratch \
	--restore \
	--restore_path log/cls/modelnet40_pointnet_scratch/checkpoints/best_model.pth ;

5) Fine Tuning Task - Semantic Segmentation

Data Usage:

For the details in the data setup, please see data/readme.md.

Training/Testing Scripts:

We unify the training and testing of all three models (PointNet, PCN and DGCNN) in train_semseg.py. We also provide the bash template for training each models from scratch, JigSaw/OcCo pre-trained checkpoints, see bash_template/train_semseg_template.sh for details:

#!/usr/bin/env bash

cd ../

# train pointnet_semseg on 6-fold cv of S3DIS, from scratch
for area in $(seq 1 1 6)
do
python train_semseg.py \
	--gpu 0,1 \
	--model pointnet_semseg \
	--bn_decay \
	--xavier_init \
	--test_area ${area} \
	--scheduler step \
	--log_dir pointnet_area${area}_scratch ;
done

# fine tune pcn_semseg on 6-fold cv of S3DIS, using jigsaw pre-trained weights
for area in $(seq 1 1 6)
do
python train_semseg.py \
	--gpu 0,1 \
	--model pcn_semseg \
	--bn_decay \
	--test_area ${area} \
	--log_dir pcn_area${area}_jigsaw \
	--restore \
	--restore_path log/jigsaw/modelnet_pcn_vanilla/checkpoints/best_model.pth ;
done

# fine tune dgcnn_semseg on 6-fold cv of S3DIS, using occo pre-trained weights
for area in $(seq 1 1 6)
do
python train_semseg.py \
	--gpu 0,1 \
	--test_area ${area} \
	--optimizer sgd \
	--scheduler cos \
	--model dgcnn_semseg \
	--log_dir dgcnn_area${area}_occo \
	--restore \
	--restore_path log/completion/modelnet_dgcnn_vanilla/checkpoints/best_model.pth ;
done

# test pointnet_semseg on 6-fold cv of S3DIS, from saved checkpoints
for area in $(seq 1 1 6)
do
python train_semseg.py \
	--gpu 0,1 \
	--mode test \
	--model pointnet_semseg \
	--test_area ${area} \
	--scheduler step \
	--log_dir pointnet_area${area}_scratch \
	--restore \
	--restore_path log/semseg/pointnet_area${area}_scratch/checkpoints/best_model.pth ;
done
Visualization:

We recommended using relevant code snippets in RandLA-Net for visualization.

6) Fine Tuning Task - Part Segmentation

Data Usage:

For the details in the data setup, please see data/readme.md.

Training/Testing Scripts:

We unify the training and testing of all three models (PointNet, PCN and DGCNN) in train_partseg.py. We also provide the bash template for training each models from scratch, JigSaw/OcCo pre-trained checkpoints, see bash_template/train_partseg_template.sh for details:

#!/usr/bin/env bash

cd ../

# training pointnet on ShapeNetPart, from scratch
python train_partseg.py \
	--gpu 0 \
	--normal \
	--bn_decay \
	--xavier_init \
	--model pointnet_partseg \
    --log_dir pointnet_scratch ;


# fine tuning pcn on ShapeNetPart, using jigsaw pre-trained checkpoints
python train_partseg.py \
	--gpu 0 \
	--normal \
	--bn_decay \
	--xavier_init \
	--model pcn_partseg \
	--log_dir pcn_jigsaw \
	--restore \
	--restore_path log/jigsaw/modelnet_pcn_vanilla/checkpoints/best_model.pth ;


# fine tuning dgcnn on ShapeNetPart, using occo pre-trained checkpoints
python train_partseg.py \
	--gpu 0,1 \
	--normal \
	--use_sgd \
	--xavier_init \
	--scheduler cos \
	--model dgcnn_partseg \
	--log_dir dgcnn_occo \
	--restore \
	--restore_path log/completion/modelnet_dgcnn_vanilla/checkpoints/best_model.pth ;


# test fine tuned pointnet on ShapeNetPart, using multiple votes
python train_partseg.py \
	--gpu 1 \
	--epoch 1 \
	--mode test \
	--num_votes 3 \
	--model pointnet_partseg \
	--log_dir pointnet_scratch \
	--restore \
	--restore_path log/partseg/pointnet_occo/checkpoints/best_model.pth ;

6) OcCo Data Generation (Create Your Own Dataset for OcCo Pre-Training)

For the details in the self-occluded point cloud generation, please see render/readme.md.

7) Just Completion (Complete Your Own Data with Pre-Trained Model)

You can use it for completing your occluded point cloud data with our provided OcCo checkpoints.

8) Jigsaw Puzzle

We also provide our implementation (developed from scratch) on pre-training point cloud models via solving 3d jigsaw puzzles tasks as well as data generation, the method is described in this paper, while the authors did not reprocess to our code request. The details of our implementation is reported in our paper appendix.

For the details of our implementation, please refer to description in the appendix of our paper and relevant code snippets, i.e., train_jigsaw.py, utils/3DPC_Data_Gen.py and train_jigsaw_template.sh.

Results

Generated Dataset:

image

Completed Occluded Point Cloud:

-- PointNet:

image

-- PCN:

image

-- DGCNN:

image

-- Failure Examples:

image

Visualization of learned features:

image

Classification (linear SVM):

image

Classification:

image

##### Semantic Segmentation:

image

##### Part Segmentation:

image

Sample Efficiency:

image

Learning Efficiency:

image

For the description and discussion of the results, please refer to our paper, thanks :)

Contributing

The code of this project is released under the MIT License.

We would like to thank and acknowledge referenced codes from the following repositories:

https://github.com/wentaoyuan/pcn

https://github.com/hansen7/NRS_3D

https://github.com/WangYueFt/dgcnn

https://github.com/charlesq34/pointnet

https://github.com/charlesq34/pointnet2

https://github.com/PointCloudLibrary/pcl

https://github.com/AnTao97/dgcnn.pytorch

https://github.com/HuguesTHOMAS/KPConv

https://github.com/QingyongHu/RandLA-Net

https://github.com/chrdiller/pyTorchChamferDistance

https://github.com/yanx27/Pointnet_Pointnet2_pytorch

https://github.com/AnTao97/UnsupervisedPointCloudReconstruction

We appreciate the help from the supportive technicians, Peter and Raf, from Cambridge Engineering :)

Semantic segmentation models, datasets and losses implemented in PyTorch.

Semantic Segmentation in PyTorch Semantic Segmentation in PyTorch Requirements Main Features Models Datasets Losses Learning rate schedulers Data augm

Yassine 1.3k Jan 07, 2023
Source code for "FastBERT: a Self-distilling BERT with Adaptive Inference Time".

FastBERT Source code for "FastBERT: a Self-distilling BERT with Adaptive Inference Time". Good News 2021/10/29 - Code: Code of FastPLM is released on

Weijie Liu 584 Jan 02, 2023
3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021)

3DDUNET This is the code for 3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021) Conference Paper Link Dataset We use SMOID dataset

1 Jan 07, 2022
Representing Long-Range Context for Graph Neural Networks with Global Attention

Graph Augmentation Graph augmentation/self-supervision/etc. Algorithms gcn gcn+virtual node gin gin+virtual node PNA GraphTrans Augmentation methods N

UC Berkeley RISE 67 Dec 30, 2022
Unbiased Learning To Rank Algorithms (ULTRA)

This is an Unbiased Learning To Rank Algorithms (ULTRA) toolbox, which provides a codebase for experiments and research on learning to rank with human annotated or noisy labels.

71 Dec 01, 2022
A Genetic Programming platform for Python with TensorFlow for wicked-fast CPU and GPU support.

Karoo GP Karoo GP is an evolutionary algorithm, a genetic programming application suite written in Python which supports both symbolic regression and

Kai Staats 149 Jan 09, 2023
The official PyTorch code for 'DER: Dynamically Expandable Representation for Class Incremental Learning' accepted by CVPR2021

DER.ClassIL.Pytorch This repo is the official implementation of DER: Dynamically Expandable Representation for Class Incremental Learning (CVPR 2021)

rhyssiyan 108 Jan 01, 2023
Layer 7 DDoS Panel with Cloudflare Bypass ( UAM, CAPTCHA, BFM, etc.. )

Blood Deluxe DDoS DDoS Attack Panel includes CloudFlare Bypass (UAM, CAPTCHA, BFM, etc..)(It works intermittently. Working on it) Don't attack any web

272 Nov 01, 2022
A big endian Gentoo port developed on a Pine64.org RockPro64

Gentoo-aarch64_be A big endian Gentoo port developed on a Pine64.org RockPro64 The endian wars are over... little endian won. As a result, it is incre

Rory Bolt 6 Dec 07, 2022
Faster RCNN pytorch windows

Faster-RCNN-pytorch-windows Faster RCNN implementation with pytorch for windows Open cmd, compile this comands: cd lib python setup.py build develop T

Hwa-Rang Kim 1 Nov 11, 2022
Code for the head detector (HeadHunter) proposed in our CVPR 2021 paper Tracking Pedestrian Heads in Dense Crowd.

Head Detector Code for the head detector (HeadHunter) proposed in our CVPR 2021 paper Tracking Pedestrian Heads in Dense Crowd. The head_detection mod

Ramana Sundararaman 76 Dec 06, 2022
Assginment for UofT CSC420: Intro to Image Understanding

Run the code Open edge_detection.ipynb in google colab. Upload image1.jpg,image2.jpg and my_image.jpg to '/content/drive/My Drive'. chooose 'Run all'

Ziyi-Zhou 1 Feb 24, 2022
Image segmentation with private İstanbul Dataset

Image Segmentation This repo was created for academic research and test result. Repo will update after academic article online. This repo contains wei

İrem KÖMÜRCÜ 9 Dec 11, 2022
Data and Code for paper Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graph is available for research purposes.

Data and Code for paper Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graph is available f

Yongrui Chen 5 Nov 10, 2022
PenguinSpeciesPredictionML - Basic model to predict Penguin species based on beak size and sex.

Penguin Species Prediction (ML) 🐧 👨🏽‍💻 What? 💻 This project is a basic model using sklearn methods to predict Penguin species based on beak size

Tucker Paron 0 Jan 08, 2022
PyTorch implementation for our paper "Deep Facial Synthesis: A New Challenge"

FSGAN Here is the official PyTorch implementation for our paper "Deep Facial Synthesis: A New Challenge". This project achieve the translation between

Deng-Ping Fan 32 Oct 10, 2022
"Neural Turing Machine" in Tensorflow

Neural Turing Machine in Tensorflow Tensorflow implementation of Neural Turing Machine. This implementation uses an LSTM controller. NTM models with m

Taehoon Kim 1k Dec 06, 2022
Randomized Correspondence Algorithm for Structural Image Editing

===================================== README: Inpainting based PatchMatch ===================================== @Author: Younesse ANDAM @Conta

Younesse 116 Dec 24, 2022
[ICCV'2021] "SSH: A Self-Supervised Framework for Image Harmonization", Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang

SSH: A Self-Supervised Framework for Image Harmonization (ICCV 2021) code for SSH Representative Examples Main Pipeline RealHM DataSet Google Drive Pr

VITA 86 Dec 02, 2022
Official implementation of the paper 'Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution' in CVPR 2022

LDL Paper | Supplementary Material Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution Jie Liang*, Hu

150 Dec 26, 2022