Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

Overview

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set —— PyTorch implementation

This is an unofficial official pytorch implementation of the following paper:

Y. Deng, J. Yang, S. Xu, D. Chen, Y. Jia, and X. Tong, Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set, IEEE Computer Vision and Pattern Recognition Workshop (CVPRW) on Analysis and Modeling of Faces and Gestures (AMFG), 2019. (Best Paper Award!)

The method enforces a hybrid-level weakly-supervised training for CNN-based 3D face reconstruction. It is fast, accurate, and robust to pose and occlussions. It achieves state-of-the-art performance on multiple datasets such as FaceWarehouse, MICC Florence and NoW Challenge.

For the original tensorflow implementation, check this repo.

This implementation is written by S. Xu.

Performance

● Reconstruction accuracy

The pytorch implementation achieves lower shape reconstruction error (9% improvement) compare to the original tensorflow implementation. Quantitative evaluation (average shape errors in mm) on several benchmarks is as follows:

Method FaceWareHouse MICC Florence NoW Challenge
Deep3DFace Tensorflow 1.81±0.50 1.67±0.50 1.54±1.29
Deep3DFace PyTorch 1.64±0.50 1.53±0.45 1.41±1.21

The comparison result with state-of-the-art public 3D face reconstruction methods on the NoW face benchmark is as follows:

Rank Method Median(mm) Mean(mm) Std(mm)
1. DECA[Feng et al., SIGGRAPH 2021] 1.09 1.38 1.18
2. Deep3DFace PyTorch 1.11 1.41 1.21
3. RingNet [Sanyal et al., CVPR 2019] 1.21 1.53 1.31
4. Deep3DFace [Deng et al., CVPRW 2019] 1.23 1.54 1.29
5. 3DDFA-V2 [Guo et al., ECCV 2020] 1.23 1.57 1.39
6. MGCNet [Shang et al., ECCV 2020] 1.31 1.87 2.63
7. PRNet [Feng et al., ECCV 2018] 1.50 1.98 1.88
8. 3DMM-CNN [Tran et al., CVPR 2017] 1.84 2.33 2.05

For more details about the evaluation, check Now Challenge website.

● Visual quality

The pytorch implementation achieves better visual consistency with the input images compare to the original tensorflow version.

● Speed

The training speed is on par with the original tensorflow implementation. For more information, see here.

Major changes

● Differentiable renderer

We use Nvdiffrast which is a pytorch library that provides high-performance primitive operations for rasterization-based differentiable rendering. The original tensorflow implementation used tf_mesh_renderer instead.

● Face recognition model

We use Arcface, a state-of-the-art face recognition model, for perceptual loss computation. By contrast, the original tensorflow implementation used Facenet.

● Training configuration

Data augmentation is used in the training process which contains random image shifting, scaling, rotation, and flipping. We also enlarge the training batchsize from 5 to 32 to stablize the training process.

● Training data

We use an extra high quality face image dataset FFHQ to increase the diversity of training data.

Requirements

This implementation is only tested under Ubuntu environment with Nvidia GPUs and CUDA installed.

Installation

  1. Clone the repository and set up a conda environment with all dependencies as follows:
git clone https://github.com/sicxu/Deep3DFaceRecon_pytorch.git --recursive
cd Deep3DFaceRecon_pytorch
conda env create -f environment.yml
source activate deep3d_pytorch
  1. Install Nvdiffrast library:
cd nvdiffrast    # ./Deep3DFaceRecon_pytorch/nvdiffrast
pip install .
  1. Install Arcface Pytorch:
cd ..    # ./Deep3DFaceRecon_pytorch
git clone https://github.com/deepinsight/insightface.git
cp -r ./insightface/recognition/arcface_torch/ ./models/

Inference with a pre-trained model

Prepare prerequisite models

  1. Our method uses Basel Face Model 2009 (BFM09) to represent 3d faces. Get access to BFM09 using this link. After getting the access, download "01_MorphableModel.mat". In addition, we use an Expression Basis provided by Guo et al.. Download the Expression Basis (Exp_Pca.bin) using this link (google drive). Organize all files into the following structure:
Deep3DFaceRecon_pytorch
│
└─── BFM
    │
    └─── 01_MorphableModel.mat
    │
    └─── Exp_Pca.bin
    |
    └─── ...
  1. We provide a model trained on a combination of CelebA, LFW, 300WLP, IJB-A, LS3D-W, and FFHQ datasets. Download the pre-trained model using this link (google drive) and organize the directory into the following structure:
Deep3DFaceRecon_pytorch
│
└─── checkpoints
    │
    └─── <model_name>
        │
        └─── epoch_20.pth

Test with custom images

To reconstruct 3d faces from test images, organize the test image folder as follows:

Deep3DFaceRecon_pytorch
│
└─── <folder_to_test_images>
    │
    └─── *.jpg/*.png
    |
    └─── detections
        |
	└─── *.txt

The *.jpg/*.png files are test images. The *.txt files are detected 5 facial landmarks with a shape of 5x2, and have the same name as the corresponding images. Check ./datasets/examples for a reference.

Then, run the test script:

# get reconstruction results of your custom images
python test.py --name=<model_name> --epoch=20 --img_folder=<folder_to_test_images>

# get reconstruction results of example images
python test.py --name=<model_name> --epoch=20 --img_folder=./datasets/examples

Results will be saved into ./checkpoints/<model_name>/results/<folder_to_test_images>, which contain the following files:

*.png A combination of cropped input image, reconstructed image, and visualization of projected landmarks.
*.obj Reconstructed 3d face mesh with predicted color (texture+illumination) in the world coordinate space. Best viewed in Meshlab.
*.mat Predicted 257-dimensional coefficients and 68 projected 2d facial landmarks. Best viewd in Matlab.

Training a model from scratch

Prepare prerequisite models

  1. We rely on Arcface to extract identity features for loss computation. Download the pre-trained model from Arcface using this link. By default, we use the resnet50 backbone (ms1mv3_arcface_r50_fp16), organize the download files into the following structure:
Deep3DFaceRecon_pytorch
│
└─── checkpoints
    │
    └─── recog_model
        │
        └─── ms1mv3_arcface_r50_fp16
	    |
	    └─── backbone.pth
  1. We initialize R-Net using the weights trained on ImageNet. Download the weights provided by PyTorch using this link, and organize the file as the following structure:
Deep3DFaceRecon_pytorch
│
└─── checkpoints
    │
    └─── init_model
        │
        └─── resnet50-0676ba61.pth
  1. We provide a landmark detector (tensorflow model) to extract 68 facial landmarks for loss computation. The detector is trained on 300WLP, LFW, and LS3D-W datasets. Download the trained model using this link (google drive) and organize the file as follows:
Deep3DFaceRecon_pytorch
│
└─── checkpoints
    │
    └─── lm_model
        │
        └─── 68lm_detector.pb

Data preparation

  1. To train a model with custom images,5 facial landmarks of each image are needed in advance for an image pre-alignment process. We recommend using dlib or MTCNN to detect these landmarks. Then, organize all files into the following structure:
Deep3DFaceRecon_pytorch
│
└─── datasets
    │
    └─── <folder_to_training_images>
        │
        └─── *.png/*.jpg
	|
	└─── detections
            |
	    └─── *.txt

The *.txt files contain 5 facial landmarks with a shape of 5x2, and should have the same name with their corresponding images.

  1. Generate 68 landmarks and skin attention mask for images using the following script:
# preprocess training images
python data_preparation.py --img_folder <folder_to_training_images>

# alternatively, you can preprocess multiple image folders simultaneously
python data_preparation.py --img_folder <folder_to_training_images1> <folder_to_training_images2> <folder_to_training_images3>

# preprocess validation images
python data_preparation.py --img_folder <folder_to_validation_images> --mode=val

The script will generate files of landmarks and skin masks, and save them into ./datasets/<folder_to_training_images>. In addition, it also generates a file containing the path of all training data into ./datalist which will then be used in the training script.

Train the face reconstruction network

Run the following script to train a face reconstruction model using the pre-processed data:

# train with single GPU
python train.py --name=<custom_experiment_name> --gpu_ids=0

# train with multiple GPUs
python train.py --name=<custom_experiment_name> --gpu_ids=0,1

# train with other custom settings
python train.py --name=<custom_experiment_name> --gpu_ids=0 --batch_size=32 --n_epochs=20

Training logs and model parameters will be saved into ./checkpoints/<custom_experiment_name>.

By default, the script uses a batchsize of 32 and will train the model with 20 epochs. For reference, the pre-trained model in this repo is trained with the default setting on a image collection of 300k images. A single iteration takes 0.8~0.9s on a single Tesla M40 GPU. The total training process takes around two days.

To use a trained model, see Inference section.

Contact

If you have any questions, please contact the paper authors.

Citation

Please cite the following paper if this model helps your research:

@inproceedings{deng2019accurate,
    title={Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set},
    author={Yu Deng and Jiaolong Yang and Sicheng Xu and Dong Chen and Yunde Jia and Xin Tong},
    booktitle={IEEE Computer Vision and Pattern Recognition Workshops},
    year={2019}
}

The face images on this page are from the public CelebA dataset released by MMLab, CUHK.

Part of the code in this implementation takes CUT as a reference.

Owner
Sicheng Xu
Sicheng Xu
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

Dense Passage Retrieval Dense Passage Retrieval (DPR) - is a set of tools and models for state-of-the-art open-domain Q&A research. It is based on the

Meta Research 1.1k Jan 03, 2023
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

Detecting Twenty-thousand Classes using Image-level Supervision Detic: A Detector with image classes that can use image-level labels to easily train d

Meta Research 1.3k Jan 04, 2023
Malware Analysis Neural Network project.

MalanaNeuralNetwork Description Malware Analysis Neural Network project. Table of Contents Getting Started Requirements Installation Clone Set-Up VENV

2 Nov 13, 2021
AlphaNet Improved Training of Supernet with Alpha-Divergence

AlphaNet: Improved Training of Supernet with Alpha-Divergence This repository contains our PyTorch training code, evaluation code and pretrained model

Facebook Research 87 Oct 10, 2022
Iris prediction model is used to classify iris species created julia's DecisionTree, DataFrames, JLD2, PlotlyJS and Statistics packages.

Iris Species Predictor Iris prediction is used to classify iris species using their sepal length, sepal width, petal length and petal width created us

Siva Prakash 2 Jan 06, 2022
[SDM 2022] Towards Similarity-Aware Time-Series Classification

SimTSC This is the PyTorch implementation of SDM2022 paper Towards Similarity-Aware Time-Series Classification. We propose Similarity-Aware Time-Serie

Daochen Zha 49 Dec 27, 2022
NR-GAN: Noise Robust Generative Adversarial Networks

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter Code and checkpoints for the ACL2021 paper "Lexicon Enhanced Chinese Sequence Labelling

Takuhiro Kaneko 59 Dec 11, 2022
Scalable and Elastic Deep Reinforcement Learning Using PyTorch. Please star. 🔥

ElegantRL “小雅”: Scalable and Elastic Deep Reinforcement Learning ElegantRL is developed for researchers and practitioners with the following advantage

AI4Finance Foundation 2.5k Jan 05, 2023
A PyTorch implementation of the continual learning experiments with deep neural networks

Brain-Inspired Replay A PyTorch implementation of the continual learning experiments with deep neural networks described in the following paper: Brain

182 Dec 27, 2022
PyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"

PASS - Official PyTorch Implementation [CVPR2021 Oral] Prototype Augmentation and Self-Supervision for Incremental Learning Fei Zhu, Xu-Yao Zhang, Chu

67 Dec 27, 2022
Code for approximate graph reduction techniques for cardinality-based DSFM, from paper

SparseCard Code for approximate graph reduction techniques for cardinality-based DSFM, from paper "Approximate Decomposable Submodular Function Minimi

Nate Veldt 1 Nov 25, 2022
Parallel and High-Fidelity Text-to-Lip Generation; AAAI 2022 ; Official code

Parallel and High-Fidelity Text-to-Lip Generation This repository is the official PyTorch implementation of our AAAI-2022 paper, in which we propose P

Zhying 77 Dec 21, 2022
A Partition Filter Network for Joint Entity and Relation Extraction EMNLP 2021

EMNLP 2021 - A Partition Filter Network for Joint Entity and Relation Extraction

zhy 127 Jan 04, 2023
Unofficial Pytorch Implementation of WaveGrad2

WaveGrad 2 — Unofficial PyTorch Implementation WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis Unofficial PyTorch+Lightning Implementati

MINDs Lab 104 Nov 29, 2022
Offical implementation of Shunted Self-Attention via Multi-Scale Token Aggregation

Shunted Transformer This is the offical implementation of Shunted Self-Attention via Multi-Scale Token Aggregation by Sucheng Ren, Daquan Zhou, Shengf

156 Dec 27, 2022
Simple Linear 2nd ODE Solver GUI - A 2nd constant coefficient linear ODE solver with simple GUI using euler's method

Simple_Linear_2nd_ODE_Solver_GUI Description It is a 2nd constant coefficient li

:) 4 Feb 05, 2022
The fastai book, published as Jupyter Notebooks

English / Spanish / Korean / Chinese / Bengali / Indonesian The fastai book These notebooks cover an introduction to deep learning, fastai, and PyTorc

fast.ai 17k Jan 07, 2023
An introduction to bioimage analysis - http://bioimagebook.github.io

Introduction to Bioimage Analysis This book tries explain the main ideas of image analysis in a practical and engaging way. It's written primarily for

Bioimage Book 20 Nov 28, 2022
Face and Pose detector that emits MQTT events when a face or human body is detected and not detected.

Face Detect MQTT Face or Pose detector that emits MQTT events when a face or human body is detected and not detected. I built this as an alternative t

Jacob Morris 38 Oct 21, 2022
Inhomogeneous Social Recommendation with Hypergraph Convolutional Networks

Inhomogeneous Social Recommendation with Hypergraph Convolutional Networks This is our Pytorch implementation for the paper: Zirui Zhu, Chen Gao, Xu C

Zirui Zhu 3 Dec 30, 2022