This project is associated with our survey paper which comprehensively contextualizes the advance of the recent AI-Generated Images as Data Source (AIGS) and visual AIGC by formulating taxonomies according to methodologies and applications.
AI-Generated Images as Data Source: The Dawn of Synthetic Era [Paper]
Zuhao Yang, Fangneng Zhan, Kunhao Liu, Muyu Xu, Shijian Lu
arXiv, 2023
The process to submit a pull request:
- a. Fork the project into your own repository.
- b. Add the Title, Author, Conference, Paper link, Project link, and Code link in
README.mdwith below format:
**Title**<br>
*Author*<br>
Conference
[[Paper](Paper link)]
[[Project](Project link)]
[[Code](Code link)]
[[Video](Video link)]
- c. Submit the pull request to this branch.
Machine Learning for Synthetic Data Generation: A Review
Yingzhou Lu, Minjie Shen, Huazheng Wang, Wenqi Wei
arXiv 2023 [Paper]
Synthetic Data in Human Analysis: A Survey
Indu Joshi, Marcel Grimmer, Christian Rathgeb, Christoph Busch, Francois Bremond, Antitza Dantcheva
arXiv 2022 [Paper]
A Review of Synthetic Image Data and Its Use in Computer Vision
Keith Man, Javaan Chahl
J. Imaging 2022 [Paper]
Survey on Synthetic Data Generation, Evaluation Methods and GANs
Alvaro Figueira, Bruno Vaz
Mathematics 2022 [Paper]
Synthetic Data for Training:
Synthetic Data Application:
Datasets:
DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Yuxuan Zhang, Huan Ling, Jun Gao, Kangxue Yin, Jean-Francois Lafleche, Adela Barriuso, Antonio Torralba, Sanja Fidler
CVPR 2021 [Paper][Project][Code]
BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations
Daiqing Li, Huan Ling, Seung Wook Kim, Karsten Kreis, Adela Barriuso, Sanja Fidler, Antonio Torralba
CVPR 2022 [Paper][Project][Code]
HandsOff: Labeled Dataset Generation With No Additional Human Annotations
On the generation of realistic synthetic petrographic datasets using a style-based GAN
Learning to Annotate Part Segmentation with Gradient Matching
Histopathology DatasetGAN: Synthesizing Large-Resolution Histopathology Datasets
Application of DatasetGAN in medical imaging: preliminary studies
Medical Image Segmentation Using Deep Learning: A Survey
Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation
A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images Using a GAN
A data augmentation perspective on diffusion models and retrieval
Max F. Burg, Florian Wenzel, Dominik Zietlow, Max Horn, Osama Makansi, Francesco Locatello, Chris Russell
arXiv 2023 [Paper]
Effective Data Augmentation With Diffusion Models
Brandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan Salakhutdinov
arXiv 2023 [Paper][Project]
Skin Lesion Classification Using GAN based Data Augmentation
Rashid Haroon, Tanveer M. Asjid, Aqeel Khan Hassan
EMBC 2019 [Paper]
GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification
Data augmentation generative adversarial networks
Gan augmentation: Augmenting training data using generative adversarial networks
Enhancement of Image Classification Using Transfer Learning and GAN-Based Synthetic Data Augmentation
Diversify your vision datasets with automatic diffusion-based augmentation
Is synthetic data from generative models ready for image recognition?
Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Song Bai, Xiaojuan Qi
ICLR 2023 [Paper][Code]
Synthetic Data from Diffusion Models Improves ImageNet Classification
Shekoofeh Azizi, Simon Kornblith, Chitwan Saharia, Mohammad Norouzi, David J. Fleet
arXiv 2023 [Paper]
Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains
Pierre Chambon, Christian Bluethgen, Curtis P. Langlotz, Akshay Chaudhari
NeurIPS 2022 [Paper]
OpenGAN: Open-Set Recognition via Open Data Generation
Shu Kong, Deva Ramanan
ICCV 2021 [Paper][Project][Code][Video]
Image Captions are Natural Prompts for Text-to-Image Models
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach
Yuhua Chen, Wen Li, Xiaoran Chen, Luc Van Gool
CVPR 2019 [Paper]
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
Daiqing Li, Junlin Yang, Karsten Kreis, Antonio Torralba, Sanja Fidler
CVPR 2021 [Paper][Project][Code]
Repurposing GANs for One-shot Semantic Part Segmentation
Nontawat Tritrong, Pitchaporn Rewatbowornwong, Supasorn Suwajanakorn
CVPR 2021 [Paper][Project][Code]
Diffusion Models for Zero-Shot Open-Vocabulary Segmentation
Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
arXiv 2023 [Paper]
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation
Weimin Tan, Siyuan Chen, Bo Yan
arXiv 2023 [Paper]
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP
ODISE
DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao, Neel Joshi, Laurent Itti, Vibhav Vineet
arXiv 2022 [Paper]
Explore the Power of Synthetic Data on Few-shot Object Detection
Shaobo Lin, Kun Wang, Xingyu Zeng, Rui Zhao
CVPR 2023 [Paper]
The Big Data Myth: Using Diffusion Models for Dataset Generation to Train Deep Detection Models
Roy Voetman, Maya Aghaei, Klaas Dijkstra
arXiv 2023 [Paper]
IMAGINARYNET: LEARNING OBJECT DETECTORS WITHOUT REAL IMAGES AND ANNOTATIONS
Integrating Geometric Control into Text-to-Image Diffusion Models for High-Quality Detection Data Generation via Text Prompt
Re-Aging GAN: Toward Personalized Face Age Transformation
Farkhod Makhmudkhujaev, Sungeun Hong, and In Kyu Park
ICCV 2021 [Paper][Video]
Only a Matter of Style: Age Transformation Using a Style-Based Regression Model
Yuval Alaluf, Or Patashnik, Daniel Cohen-Or
SIGGRAPH 2021 [Paper][Project][Code][Video]
Production-Ready Face Re-Aging for Visual Effects
Gaspard Zoss, Prashanth Chandran, Eftychios Sifakis, Markus Gross, Paulo Gotardo, Derek Bradley
TOG 2021 [Paper][Project][Video]
Zero-1-to-3: Zero-shot One Image to 3D Object
Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, Carl Vondrick
ICCV 2023 [Paper][Project][Code]
DreamBooth3D: Subject-Driven Text-to-3D Generation
Amit Raj, Srinivas Kaza, Ben Poole, Michael Niemeyer, Nataniel Ruiz, Ben Mildenhall, Shiran Zada, Kfir Aberman, Michael Rubinstein, Jonathan Barron, Yuanzhen Li, Varun Jampani
arXiv 2023 [Paper][Project][Video]
StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation
Chi Zhang, Yiwen Chen, Yijun Fu, Zhenglin Zhou, Gang YU, Billzb Wang, Bin Fu, Tao Chen, Guosheng Lin, Chunhua Shen
arXiv 2023 [Paper]
Generative Models as a Data Source for Multiview Representation Learning
Ali Jahanian, Xavier Puig, Yonglong Tian, Phillip Isola
ICLR 2022 [Paper][Project][Code][Video]
StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
Yonglong Tian, Lijie Fan, Phillip Isola, Huiwen Chang, Dilip Krishnan
arXiv 2023 [Paper]
Ensembling with Deep Generative Views
DreamTeacher: Pretraining Image Backbones with Deep Generative Models
NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields
Thomas Lips, Victor-Louis De Gusseme, Francis wyffels
ICRA 2022 [Paper][Project][Code][Video]
INeRF: Inverting Neural Radiance Fields for Pose Estimation
VMRF: View Matching Neural Radiance Fields
LENS: Localization enhanced by NeRF synthesis
Gan-based neural radiance field without posed camera
NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
Vision-only robot navigation in a neural radiance world
Event-based Camera Tracker by ∇t NeRF
Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field
3D Data Augmentation for Driving Scenes on Camera
UniSim: A Neural Closed-Loop Sensor Simulator
MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving
DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models
Zijie J. Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, Duen Horng Chau
ACL 2023 [Paper]Project][Code]
JourneyDB: A Benchmark for Generative Image Understanding
Junting Pan, Keqiang Sun, Yuying Ge, Hao Li, Haodong Duan, Xiaoshi Wu, Renrui Zhang, Aojun Zhou, Zipeng Qin, Yi Wang, Jifeng Dai, Yu Qiao, Hongsheng Li
arXiv 2023 [Paper][Project][Code]
GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image
Mingjian Zhu, Hanting Chen, Qiangyu Yan, Xudong Huang, Guanyu Lin, Wei Li, Zhijun Tu, Hailin Hu, Jie Hu, Yunhe Wang
arXiv 2023 [Paper][Project][Code]
DiffusionDB (https://huggingface.co/datasets/poloclub/diffusiondb)
JourneyDB (https://docs.google.com/forms/d/e/1FAIpQLSeiciK0g0IA46_hFaitRhdpihhpjqt3helJNT68y-C8MfKhiQ/viewform?pli=1)
GenImage (https://pan.baidu.com/share/init?surl=i0OFqYN5i6oFAxeK6bIwRQ#list/path=%2F)
If you use this code for your research, please cite our papers.
@article{yang2023aigs,
title={AI-Generated Images as Data Source: The Dawn of Synthetic Era},
author={Zuhao Yang and Fangneng Zhan and Kunhao Liu and Muyu Xu and Shijian Lu},
journal={arXiv preprint arXiv:2310.01830},
year={2023}
}