SlideShare a Scribd company logo
1 of 26
Download to read offline
Interpreting the Latent Space of
GANs for Semantic Face Editing
SATO, Ryosuke
Introduction
Paper reading
Today’s paper
Shen Y, Gu J, Tang X, Zhou B. Interpreting the latent space of gans for semantic
face editing. InProceedings of the IEEE/CVF Conference on Computer Vision and
Pattern Recognition 2020 (pp. 9243-9252).
● “we propose a novel framework, called InterFaceGAN”
● “for semantic face editing by interpreting the latent semantics learned by GANs.”
● Style GAN (or PGGAN) + disentangled latent codes
Why this paper?
CVPR accepted paper list → grep “interpret”
● ALFRED
● A Disentangling Invertible Interpretation Network for Explaining Latent Representations
● Self-supervised Learning of Interpretable Keypoints from Unlabelled Videos
● Interpreting the Latent Space of GANs for Semantic Face Editing
● Interpretable and Accurate Fine-grained Recognition via Region Grouping
TL; DR
- We are able to change images semantically (Age, Eyeglasses, …)
- Using models Style GAN or PG-GAN
Previous Research
Dataset - Celeb A
Previous Reseach
PG-GAN (Progressive Growing of GANs)
Key Points:
Growing the G and D progressively.
(grow low → high resolution.)
Previous Reseach
Style GAN
Key Points:
- Progressive Growing + AdaIN + Mixing Regularization.
- Using two latent codes (z and w).
Latent codes are disentanglement.
Previous Reseach
Image2StyleGAN
Key Points:
Optimize w from original images (like AnoGAN).
If we change w1 to w2, we can do morphing.
However, It’s not semantically.
We’d like to convert image semantically.
e.g.)male → female
smile → expressionless
Proposal method
Method
Method
meaning?
Method
1. Given a well-trained GAN model (Style GAN or PGGAN)
2. Generate z from image by the model
3. To calculate the semantic scores
4. Define the separation boundary (for m semantics)
Used m=5 key facial attributes for analysis in the paper
● Pose
● Smile (Expression)
● Age
● Gender
● Eyeglasses
5. To generate a image from z_edit
↑ This is the image edited semantically.
Method
1. Given a well-trained GAN model (Style GAN or PGGAN)
2. Generate z from image by the model
3. To calculate the semantic scores
4. Define the separation boundary (for m semantics)
Used m=5 key facial attributes for analysis in the paper
● Pose
● Smile (Expression)
● Age
● Gender
● Eyeglasses
5. To generate a image from z_edit
↑ This is the image edited semantically.
Method
To calculate the semantic scores
Method
Using with SVMs for defining the separation boundary (for m semantics)
z
Hyperplane
normal vector n Male
Female
z
z
z
Here, z can be changed semantically.
However, “when there is more than one attribute,
editing one may affect another since some
semantics can be coupled with each other.”
Method
Using with SVMs for defining the separation boundary (for m semantics)
z
Hyperplane
normal vector n Male
Female
z
z
z
Here, z can be changed semantically.
However, “when there is more than one attribute,
editing one may affect another since some
semantics can be coupled with each other.”
Method
1. To calculate the semantic scores from generated images
a. with ResNet50 trained by CelebA
b. Original scores are binary and multi-class label
2. Define the separation boundary (for m semantics)
a. using SVMs
3. Move latent codes for changing image semantically
a. manually forcing N・N to be diagonal. (named conditional manipulation)
Experimental
Experimental
pose and smile are almost
orthogonal to other attributes.
Nevertheless, gender,
age, and eyeglasses need
conditional manipulation.
(not orthogonal)
Experimental
Additional experiment
ref: StyleGANを遊び尽くせ!! 追加学習不要の画像編集-Qiita
left: Celeb A right: Novel image
Conclusion
● We can convert img1 to img2 smoothly and semantically.
● With the pretrained model, training is relatively fast.
● It may not be accurate enough to generate novel images.
Note
- Are not there any quantitative metrics of "semantically"?
References
1. Shen Y, Gu J, Tang X, Zhou B. Interpreting the latent space of gans for semantic face editing. InProceedings of the IEEE/CVF Conference
on Computer Vision and Pattern Recognition 2020 (pp. 9243-9252).
2. Karras T, Aila T, Laine S, Lehtinen J. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint
arXiv:1710.10196. 2017 Oct 27.
3. Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. InProceedings of the IEEE conference on
computer vision and pattern recognition 2019 (pp. 4401-4410).
4. Abdal R, Qin Y, Wonka P. Image2stylegan: How to embed images into the stylegan latent space?. InProceedings of the IEEE international
conference on computer vision 2019 (pp. 4432-4441).
5. StyleGANを遊び尽くせ!! ~追加学習不要の画像編集~ - Qiita https://qiita.com/pacifinapacific/items/1d6cca0ff4060e12d336
6. GANの基礎からStyleGAN2まで. この記事について| by akira | Medium
https://medium.com/@akichan_f/gan%E3%81%AE%E5%9F%BA%E7%A4%8E%E3%81%8B%E3%82%89stylegan2%E3%81%BE%E3%8
1%A7-dfd2608410b3

More Related Content

Similar to Paper reading _interpreting_the_latent_space_of_ga_ns_for_semantic_face_editing

Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsLakshmi Sarvani Videla
 
IMAGE GENERATION WITH GANS-BASED TECHNIQUES: A SURVEY
IMAGE GENERATION WITH GANS-BASED TECHNIQUES: A SURVEYIMAGE GENERATION WITH GANS-BASED TECHNIQUES: A SURVEY
IMAGE GENERATION WITH GANS-BASED TECHNIQUES: A SURVEYijcsit
 
Image Generation with Gans-based Techniques: A Survey
Image Generation with Gans-based Techniques: A SurveyImage Generation with Gans-based Techniques: A Survey
Image Generation with Gans-based Techniques: A SurveyAIRCC Publishing Corporation
 
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...IRJET Journal
 
DOMAIN ENGINEERING FOR APPLIED MONOCULAR RECONSTRUCTION OF PARAMETRIC FACES
DOMAIN ENGINEERING FOR APPLIED MONOCULAR RECONSTRUCTION OF PARAMETRIC FACESDOMAIN ENGINEERING FOR APPLIED MONOCULAR RECONSTRUCTION OF PARAMETRIC FACES
DOMAIN ENGINEERING FOR APPLIED MONOCULAR RECONSTRUCTION OF PARAMETRIC FACESsipij
 
Domain Engineering for Applied Monocular Reconstruction of Parametric Faces
Domain Engineering for Applied Monocular Reconstruction of Parametric FacesDomain Engineering for Applied Monocular Reconstruction of Parametric Faces
Domain Engineering for Applied Monocular Reconstruction of Parametric Facessipij
 
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBPHybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBPCSCJournals
 
Face Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCAFace Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCAIOSR Journals
 
Graphs for Visual Understanding
Graphs for Visual UnderstandingGraphs for Visual Understanding
Graphs for Visual UnderstandingKaushalya Madhawa
 
Tutorial on Deep Generative Models
 Tutorial on Deep Generative Models Tutorial on Deep Generative Models
Tutorial on Deep Generative ModelsMLReview
 
220510 지승현 Unpaired Image-to-Image Translation.pptx
220510 지승현 Unpaired Image-to-Image Translation.pptx220510 지승현 Unpaired Image-to-Image Translation.pptx
220510 지승현 Unpaired Image-to-Image Translation.pptxssuser23ed0c
 
M.E Computer Science Image Processing Projects
M.E Computer Science Image Processing ProjectsM.E Computer Science Image Processing Projects
M.E Computer Science Image Processing ProjectsVijay Karan
 
M.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsM.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsVijay Karan
 
M.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsM.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsVijay Karan
 
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and AbstractIEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and Abstracttsysglobalsolutions
 
更適應性的AOI-深度強化學習之應用
更適應性的AOI-深度強化學習之應用更適應性的AOI-深度強化學習之應用
更適應性的AOI-深度強化學習之應用CHENHuiMei
 
Ieee transactions on image processing
Ieee transactions on image processingIeee transactions on image processing
Ieee transactions on image processingtsysglobalsolutions
 

Similar to Paper reading _interpreting_the_latent_space_of_ga_ns_for_semantic_face_editing (20)

Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point Clouds
 
IMAGE GENERATION WITH GANS-BASED TECHNIQUES: A SURVEY
IMAGE GENERATION WITH GANS-BASED TECHNIQUES: A SURVEYIMAGE GENERATION WITH GANS-BASED TECHNIQUES: A SURVEY
IMAGE GENERATION WITH GANS-BASED TECHNIQUES: A SURVEY
 
Image Generation with Gans-based Techniques: A Survey
Image Generation with Gans-based Techniques: A SurveyImage Generation with Gans-based Techniques: A Survey
Image Generation with Gans-based Techniques: A Survey
 
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
Human Face Detection and Tracking for Age Rank, Weight and Gender Estimation ...
 
DOMAIN ENGINEERING FOR APPLIED MONOCULAR RECONSTRUCTION OF PARAMETRIC FACES
DOMAIN ENGINEERING FOR APPLIED MONOCULAR RECONSTRUCTION OF PARAMETRIC FACESDOMAIN ENGINEERING FOR APPLIED MONOCULAR RECONSTRUCTION OF PARAMETRIC FACES
DOMAIN ENGINEERING FOR APPLIED MONOCULAR RECONSTRUCTION OF PARAMETRIC FACES
 
Domain Engineering for Applied Monocular Reconstruction of Parametric Faces
Domain Engineering for Applied Monocular Reconstruction of Parametric FacesDomain Engineering for Applied Monocular Reconstruction of Parametric Faces
Domain Engineering for Applied Monocular Reconstruction of Parametric Faces
 
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBPHybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
 
Face Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCAFace Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCA
 
Graphs for Visual Understanding
Graphs for Visual UnderstandingGraphs for Visual Understanding
Graphs for Visual Understanding
 
Tutorial on Deep Generative Models
 Tutorial on Deep Generative Models Tutorial on Deep Generative Models
Tutorial on Deep Generative Models
 
220510 지승현 Unpaired Image-to-Image Translation.pptx
220510 지승현 Unpaired Image-to-Image Translation.pptx220510 지승현 Unpaired Image-to-Image Translation.pptx
220510 지승현 Unpaired Image-to-Image Translation.pptx
 
ppt[1].pptx
ppt[1].pptxppt[1].pptx
ppt[1].pptx
 
M.E Computer Science Image Processing Projects
M.E Computer Science Image Processing ProjectsM.E Computer Science Image Processing Projects
M.E Computer Science Image Processing Projects
 
M.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsM.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing Projects
 
M.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsM.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing Projects
 
BeautyGlow
BeautyGlowBeautyGlow
BeautyGlow
 
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and AbstractIEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
 
更適應性的AOI-深度強化學習之應用
更適應性的AOI-深度強化學習之應用更適應性的AOI-深度強化學習之應用
更適應性的AOI-深度強化學習之應用
 
H0334749
H0334749H0334749
H0334749
 
Ieee transactions on image processing
Ieee transactions on image processingIeee transactions on image processing
Ieee transactions on image processing
 

Recently uploaded

W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...panagenda
 
How To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.jsHow To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.jsAndolasoft Inc
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...Health
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsArshad QA
 
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️anilsa9823
 
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfThe Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfkalichargn70th171
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️Delhi Call girls
 
5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdf5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdfWave PLM
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providermohitmore19
 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...MyIntelliSource, Inc.
 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...harshavardhanraghave
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVshikhaohhpro
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...ICS
 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfkalichargn70th171
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comFatema Valibhai
 
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Steffen Staab
 
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...OnePlan Solutions
 
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...MyIntelliSource, Inc.
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxComplianceQuest1
 

Recently uploaded (20)

W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
 
How To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.jsHow To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.js
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview Questions
 
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
 
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfThe Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
 
5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdf5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdf
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTV
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.com
 
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
 
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
 
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
 
Microsoft AI Transformation Partner Playbook.pdf
Microsoft AI Transformation Partner Playbook.pdfMicrosoft AI Transformation Partner Playbook.pdf
Microsoft AI Transformation Partner Playbook.pdf
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docx
 

Paper reading _interpreting_the_latent_space_of_ga_ns_for_semantic_face_editing

  • 1. Interpreting the Latent Space of GANs for Semantic Face Editing SATO, Ryosuke
  • 3. Paper reading Today’s paper Shen Y, Gu J, Tang X, Zhou B. Interpreting the latent space of gans for semantic face editing. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020 (pp. 9243-9252). ● “we propose a novel framework, called InterFaceGAN” ● “for semantic face editing by interpreting the latent semantics learned by GANs.” ● Style GAN (or PGGAN) + disentangled latent codes
  • 4. Why this paper? CVPR accepted paper list → grep “interpret” ● ALFRED ● A Disentangling Invertible Interpretation Network for Explaining Latent Representations ● Self-supervised Learning of Interpretable Keypoints from Unlabelled Videos ● Interpreting the Latent Space of GANs for Semantic Face Editing ● Interpretable and Accurate Fine-grained Recognition via Region Grouping
  • 5. TL; DR - We are able to change images semantically (Age, Eyeglasses, …) - Using models Style GAN or PG-GAN
  • 8. Previous Reseach PG-GAN (Progressive Growing of GANs) Key Points: Growing the G and D progressively. (grow low → high resolution.)
  • 9. Previous Reseach Style GAN Key Points: - Progressive Growing + AdaIN + Mixing Regularization. - Using two latent codes (z and w). Latent codes are disentanglement.
  • 10. Previous Reseach Image2StyleGAN Key Points: Optimize w from original images (like AnoGAN). If we change w1 to w2, we can do morphing. However, It’s not semantically. We’d like to convert image semantically. e.g.)male → female smile → expressionless
  • 14. Method 1. Given a well-trained GAN model (Style GAN or PGGAN) 2. Generate z from image by the model 3. To calculate the semantic scores 4. Define the separation boundary (for m semantics) Used m=5 key facial attributes for analysis in the paper ● Pose ● Smile (Expression) ● Age ● Gender ● Eyeglasses 5. To generate a image from z_edit ↑ This is the image edited semantically.
  • 15. Method 1. Given a well-trained GAN model (Style GAN or PGGAN) 2. Generate z from image by the model 3. To calculate the semantic scores 4. Define the separation boundary (for m semantics) Used m=5 key facial attributes for analysis in the paper ● Pose ● Smile (Expression) ● Age ● Gender ● Eyeglasses 5. To generate a image from z_edit ↑ This is the image edited semantically.
  • 16. Method To calculate the semantic scores
  • 17. Method Using with SVMs for defining the separation boundary (for m semantics) z Hyperplane normal vector n Male Female z z z Here, z can be changed semantically. However, “when there is more than one attribute, editing one may affect another since some semantics can be coupled with each other.”
  • 18. Method Using with SVMs for defining the separation boundary (for m semantics) z Hyperplane normal vector n Male Female z z z Here, z can be changed semantically. However, “when there is more than one attribute, editing one may affect another since some semantics can be coupled with each other.”
  • 19.
  • 20. Method 1. To calculate the semantic scores from generated images a. with ResNet50 trained by CelebA b. Original scores are binary and multi-class label 2. Define the separation boundary (for m semantics) a. using SVMs 3. Move latent codes for changing image semantically a. manually forcing N・N to be diagonal. (named conditional manipulation)
  • 22. Experimental pose and smile are almost orthogonal to other attributes. Nevertheless, gender, age, and eyeglasses need conditional manipulation. (not orthogonal)
  • 23.
  • 24. Experimental Additional experiment ref: StyleGANを遊び尽くせ!! 追加学習不要の画像編集-Qiita left: Celeb A right: Novel image
  • 25. Conclusion ● We can convert img1 to img2 smoothly and semantically. ● With the pretrained model, training is relatively fast. ● It may not be accurate enough to generate novel images. Note - Are not there any quantitative metrics of "semantically"?
  • 26. References 1. Shen Y, Gu J, Tang X, Zhou B. Interpreting the latent space of gans for semantic face editing. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020 (pp. 9243-9252). 2. Karras T, Aila T, Laine S, Lehtinen J. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196. 2017 Oct 27. 3. Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. InProceedings of the IEEE conference on computer vision and pattern recognition 2019 (pp. 4401-4410). 4. Abdal R, Qin Y, Wonka P. Image2stylegan: How to embed images into the stylegan latent space?. InProceedings of the IEEE international conference on computer vision 2019 (pp. 4432-4441). 5. StyleGANを遊び尽くせ!! ~追加学習不要の画像編集~ - Qiita https://qiita.com/pacifinapacific/items/1d6cca0ff4060e12d336 6. GANの基礎からStyleGAN2まで. この記事について| by akira | Medium https://medium.com/@akichan_f/gan%E3%81%AE%E5%9F%BA%E7%A4%8E%E3%81%8B%E3%82%89stylegan2%E3%81%BE%E3%8 1%A7-dfd2608410b3