Occlusion robust 3D face reconstruction model in CFR-GAN (WACV 2022)

Overview

Occlusion Robust 3D face Reconstruction

Yeong-Joon Ju, Gun-Hee Lee, Jung-Ho Hong, and Seong-Whan Lee

Code for Occlusion Robust 3D Face Reconstruction in "Complete Face Recovery GAN: Unsupervised Joint Face Rotation and De-Occlusion from a Single-View Image (WACV 2022)"

We propose our novel two stage fine-tuning strategy for occlusion-robust 3D face reconstruction. The training method is split into two training stages due to the difficulty of initial training for extreme occlusions. We fine-tune the baseline with our newly created datasets in the first stage and with teacher-student learning method in the second stage.

Our baseline is Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set and we also referred this code. Note that we focus on alignments and colors for guidance of CFR-GAN in occluded facial images.

Requirements


Usage


Preprocessing:

Prepare your own dataset for data augmentation. The datasets used in this paper can be downloaded in follows:

Except when the dataset has facial landmarks labels, you should predict facial landmarks. We recommend using 3DDFA v2. If you want to reduce error propagation of the facial alignment networks, prepend a flag to filename. (ex) "pred"+[filename])

In order to train occlusion-robust 3D face model, occluded face image datasets are essential, but they are absent. So, we create datasets by synthesizing the hand-shape mask.

python create_train_stage1.py --img_path [your image folder] --lmk_path [your landmarks folder] --save_path [path to save]

For first training stage, prepare occluded (augmented images), ori_img (original images), landmarks (3D landmarks) folders or modify folder name in train_stage1.py.

**You must align images with align.py**

meta file format is:

[filename] left eye x left eye y right eye x right eye y nose x nose y left mouth x left mouth y ...

You can use MTCNN or RetinaFace

First Fine-tuning Stage:

Instead of skin mask, we use BiseNet, face parsing network. The codes and weights were modified and re-trained from this code.

Train occlusion-robust 3D face model

python train_stage1.py

To show logs

tensorboard --logdir=logs_stage1 --bind_all --reload_multifile True

Second Fine-tuning Stage:

  • You can download MaskedFaceNet dataset in here.
  • You can download FFHQ dataset in here.

Train

python train_stage2.py

To show logs

tensorboard --logdir=logs_stage2 --bind_all --reload_multifile True

Evaluation

python evaluation/benchmark_nme_aflw_2000.py

If you would like to evaluate your results, please refer evaluation/estimate_aflw2000.py

You might also like...
This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation

SO-Pose This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation This paper is basically an

Codes of paper
Codes of paper "Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling"

Unseen Object Amodal Instance Segmentation (UOAIS) Seunghyeok Back, Joosoon Lee, Taewon Kim, Sangjun Noh, Raeyoung Kang, Seongho Bak, Kyoobin Lee This

Code for
Code for "ShineOn: Illuminating Design Choices for Practical Video-based Virtual Clothing Try-on", accepted at WACV 2021 Generation of Human Behavior Workshop.

ShineOn: Illuminating Design Choices for Practical Video-based Virtual Clothing Try-on [ Paper ] [ Project Page ] This repository contains the code fo

FuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space OptimizationFuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space Optimization
FuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space OptimizationFuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space Optimization

FuseDream This repo contains code for our paper (paper link): FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimizat

DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time
DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time

DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time Introduction This is official implementation for DR-GAN (IEEE TCS

[3DV 2020] PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction
[3DV 2020] PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction

PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction International Conference on 3D Vision, 2020 Sai Sagar Jinka1, Rohan

NR-GAN: Noise Robust Generative Adversarial Networks
NR-GAN: Noise Robust Generative Adversarial Networks

NR-GAN: Noise Robust Generative Adversarial Networks (CVPR 2020) This repository provides PyTorch implementation for noise robust GAN (NR-GAN). NR-GAN

Implementation for Paper "Inverting Generative Adversarial Renderer for Face Reconstruction"

StyleGAR TODO: add arxiv link Implementation of Inverting Generative Adversarial Renderer for Face Reconstruction TODO: for test Currently, some model

This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods from a single image under variations in viewing angle, lighting, and common occlusions.
Comments
  • About align in Preprocessing step

    About align in Preprocessing step

    Thanks for your greate work! I want to train my model following the readme file , and I noticed you remind that You must align images with align.py in Preprocessing step. So should I first execute align.py in origin datasets to get the aligned datasets, and then execute the create_train_stage1.py using the aligned datasets path as a parameter? Thanks again!

    opened by zhih-li 2
  • convert tflite?

    convert tflite?

    안녕하세요, face frontalization 일 때문에 논문하고 코드를 보고 있는데요... 모델 구성정보를 받을수 있을까요? training 하시는데 시간은 어느정도 걸리셨을까요? 이 모델을 조금 경량화한다음에 training 해서 tflite 로 변경하고 싶은데 조언 좀 받고싶습니다.

    opened by john09282922 1
Owner
Yeongjoon
Yeongjoon
[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

SADRNet Paper link: SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction Requirements python

Multimedia Computing Group, Nanjing University 97 Nov 23, 2022
Pytorch implementation of "Geometrically Adaptive Dictionary Attack on Face Recognition" (WACV 2022)

Geometrically Adaptive Dictionary Attack on Face Recognition This is the Pytorch code of our paper "Geometrically Adaptive Dictionary Attack on Face R

null 6 Nov 21, 2022
"MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction" (CVPRW 2022) & (Winner of NTIRE 2022 Challenge on Spectral Reconstruction from RGB)

MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction (CVPRW 2022) Yuanhao Cai, Jing Lin, Zudi Lin, Haoqian Wang, Yulun Z

Yuanhao Cai 266 Nov 14, 2022
[WACV 2020] Reducing Footskate in Human Motion Reconstruction with Ground Contact Constraints

Reducing Footskate in Human Motion Reconstruction with Ground Contact Constraints Official implementation for Reducing Footskate in Human Motion Recon

Virginia Tech Vision and Learning Lab 38 Nov 1, 2022
Robust Instance Segmentation through Reasoning about Multi-Object Occlusion [CVPR 2021]

Robust Instance Segmentation through Reasoning about Multi-Object Occlusion [CVPR 2021] Abstract Analyzing complex scenes with DNN is a challenging ta

Irene Yuan 24 Jun 27, 2022
The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

OC-SORT Observation-Centric SORT (OC-SORT) is a pure motion-model-based multi-object tracker. It aims to improve tracking robustness in crowded scenes

Jinkun Cao 306 Nov 29, 2022
Official PyTorch code for WACV 2022 paper "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows"

CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows WACV 2022 preprint:https://arxiv.org/abs/2107.1

Denis 150 Nov 17, 2022
Imposter-detector-2022 - HackED 2022 Team 3IQ - 2022 Imposter Detector

HackED 2022 Team 3IQ - 2022 Imposter Detector By Aneeljyot Alagh, Curtis Kan, Jo

Joshua Ji 3 Aug 20, 2022
A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

ManhattanSLAM Authors: Raza Yunus, Yanyan Li and Federico Tombari ManhattanSLAM is a real-time SLAM library for RGB-D cameras that computes the camera

null 115 Nov 5, 2022
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [BCNet, CVPR 2021] This is the official pytorch implementation of BCNet built on

Lei Ke 432 Nov 22, 2022