3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Normal Face Photos

Overview

3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Normal Face Photos

This repository contains the source code and dataset for the paper 3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Normal Face Photos by Zipeng Ye, Mengfei Xia, Yanan Sun, Ran Yi, Minjing Yu, Juyong Zhang, Yu-Kun Lai and Yong-Jin Liu, which is accepted by IEEE Transactions on Visualization and Computer Graphics (TVCG).

This repository contains two parts: dataset and source code.

2D and 3D Caricature Dataset

2D Caricature Dataset

2d_dataset

We collect 5,343 hand-drawn portrait caricature images from Pinterest.com and WebCaricature dataset with facial landmarks extracted by a landmark detector, followed by human interaction for correction if needed.

The 2D dataset is in cari_2D_dataset.zip file.

3D Caricature Dataset

3d_dataset

We use the method to generate 5,343 3D caricature meshes of the same topology. We align the pose of the generated 3D caricature meshes with the pose of a template 3D head using an ICP method, where we use 5 key landmarks in eyes, nose and mouth as the landmarks for ICP. We normalize the coordinates of the 3D caricature mesh vertices by translating the center of meshes to the origin and scaling them to the same size.

The 3D dataset is in cari_3D_dataset.zip file.

3DCariPCA

We use the 3D caricature dataset to build a PCA model. We use sklearn.decomposition.PCA to build 3DCariPCA. The PCA model is pca200_icp.model file. You could use joblib to load the model and use it.

Download

You can download the two datasets and PCA in google drive and BaiduYun (code: 3kz8).

Source Code

Running Environment

Ubuntu 16.04 + Python3.7

You can install the environment directly by using conda env create -f env.yml in conda.

Training

We use our 3D caricature dataset and CelebA-Mask-HQ dataset to train 3D-CariGAN. You could download CelebA-Mask-HQ dataset and then reconstruct their 3D normal heads of all images. The 3D normal heads are for calculating loss.

Inferring

The inferring code is cari_pipeline.py file in pipeline folder. You could train your model or use our pre-trained model.

The pipeline includes two optional sub-program eye_complete and color_complete, which are implemented by C++. You should compile them and then use them. The eye_complete is for completing the eye part of mesh and the color_complete is for texture completion.

Pre-trained Model

You can download pre-trained model latest.pth in google drive and BaiduYun (code: 3kz8). You should put it into ./checkpoints.

Additional notes

Please cite the following paper if the dataset and code help your research:

Citation:

@article{ye2021caricature,
 author = {Ye, Zipeng and Xia, Mengfei and Sun, Yanan and Yi, Ran and Yu, Minjing and Zhang, Juyong and Lai, Yu-Kun and Liu, Yong-Jin},
 title = {3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Normal Face Photos},
 journal = {IEEE Transactions on Visualization and Computer Graphics},
 year = {2021},
 doi={10.1109/TVCG.2021.3126659},
}

The paper will be published.

sssegmentation is a general framework for our research on strongly supervised semantic segmentation.

sssegmentation is a general framework for our research on strongly supervised semantic segmentation.

445 Jan 02, 2023
TCTrack: Temporal Contexts for Aerial Tracking (CVPR2022)

TCTrack: Temporal Contexts for Aerial Tracking (CVPR2022) Ziang Cao and Ziyuan Huang and Liang Pan and Shiwei Zhang and Ziwei Liu and Changhong Fu In

Intelligent Vision for Robotics in Complex Environment 100 Dec 19, 2022
A PyTorch Reimplementation of TecoGAN: Temporally Coherent GAN for Video Super-Resolution

TecoGAN-PyTorch Introduction This is a PyTorch reimplementation of TecoGAN: Temporally Coherent GAN for Video Super-Resolution (VSR). Please refer to

165 Dec 17, 2022
YOLOv5 detection interface - PyQt5 implementation

所有代码已上传,直接clone后,运行yolo_win.py即可开启界面。 2021/9/29:加入置信度选择 界面是在ultralytics的yolov5基础上建立的,界面使用pyqt5实现,内容较简单,娱乐而已。 功能: 模型选择 本地文件选择(视频图片均可) 开关摄像头

487 Dec 27, 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
A curated list of awesome Machine Learning frameworks, libraries and software.

Awesome Machine Learning A curated list of awesome machine learning frameworks, libraries and software (by language). Inspired by awesome-php. If you

Joseph Misiti 57.1k Jan 03, 2023
This repo contains implementation of different architectures for emotion recognition in conversations.

Emotion Recognition in Conversations Updates 🔥 🔥 🔥 Date Announcements 03/08/2021 🎆 🎆 We have released a new dataset M2H2: A Multimodal Multiparty

Deep Cognition and Language Research (DeCLaRe) Lab 1k Dec 30, 2022
Solver for Large-Scale Rank-One Semidefinite Relaxations

STRIDE: spectrahedral proximal gradient descent along vertices A Solver for Large-Scale Rank-One Semidefinite Relaxations About STRIDE is designed for

48 Dec 20, 2022
Explaining Deep Neural Networks - A comparison of different CAM methods based on an insect data set

Explaining Deep Neural Networks - A comparison of different CAM methods based on an insect data set This is the repository for the Deep Learning proje

Robert Krug 3 Feb 06, 2022
paper: Hyperspectral Remote Sensing Image Classification Using Deep Convolutional Capsule Network

DC-CapsNet This is a tensorflow and keras based implementation of DC-CapsNet for HSI in the Remote Sensing Letters R. Lei et al., "Hyperspectral Remot

LEI 7 Nov 29, 2022
Crossover Learning for Fast Online Video Instance Segmentation (ICCV 2021)

TL;DR: CrossVIS (Crossover Learning for Fast Online Video Instance Segmentation) proposes a novel crossover learning paradigm to fully leverage rich c

Hust Visual Learning Team 79 Nov 25, 2022
Unifying Global-Local Representations in Salient Object Detection with Transformer

GLSTR (Global-Local Saliency Transformer) This is the official implementation of paper "Unifying Global-Local Representations in Salient Object Detect

11 Aug 24, 2022
공공장소에서 눈만 돌리면 CCTV가 보인다는 말이 과언이 아닐 정도로 CCTV가 우리 생활에 깊숙이 자리 잡았습니다.

ObsCare_Main 소개 공공장소에서 눈만 돌리면 CCTV가 보인다는 말이 과언이 아닐 정도로 CCTV가 우리 생활에 깊숙이 자리 잡았습니다. CCTV의 대수가 급격히 늘어나면서 관리와 효율성 문제와 더불어, 곳곳에 설치된 CCTV를 개별 관제하는 것으로는 응급 상

5 Jul 07, 2022
Official code repository for ICCV 2021 paper: Gravity-Aware Monocular 3D Human Object Reconstruction

GraviCap Official code repository for ICCV 2021 paper: Gravity-Aware Monocular 3D Human Object Reconstruction. Gravity-Aware Monocular 3D Human-Object

Rishabh Dabral 15 Dec 09, 2022
Json2Xml tool will help you convert from json COCO format to VOC xml format in Object Detection Problem.

JSON 2 XML All codes assume running from root directory. Please update the sys path at the beginning of the codes before running. Over View Json2Xml t

Nguyễn Trường Lâu 6 Aug 22, 2022
Studying Python release adoptions by looking at PyPI downloads

Analysis of version adoptions on PyPI We get PyPI download statistics via Google's BigQuery using the pypinfo tool. Usage First you need to get an acc

Julien Palard 9 Nov 04, 2022
Official repository for Fourier model that can generate periodic signals

Conditional Generation of Periodic Signals with Fourier-Based Decoder Jiyoung Lee, Wonjae Kim, Daehoon Gwak, Edward Choi This repository provides offi

8 May 25, 2022
[CVPR 2021] NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning

NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning Project Page | Paper | Supplemental material #1 | Supplement

KAIST VCLAB 49 Nov 24, 2022
Relative Human dataset, CVPR 2022

Relative Human (RH) contains multi-person in-the-wild RGB images with rich human annotations, including: Depth layers (DLs): relative depth relationsh

Yu Sun 112 Dec 02, 2022
EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks

EncT5 (Unofficial) Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks About Finetune T5 model for classification & r

Jangwon Park 34 Jan 01, 2023