Listen to this story
From Snapchat face swap to Mona Lisa talking, DeepFake has come a long way in the field of technology. This creepy technology has given us some chills since its advancements in the face-swapping phenomenon. Recently, we have witnessed DeepFaking Jim Carrey into Jack Nicholson’s most popular cult classic The Shining, swapping Nicolas Cage’s face with John Travolta’s 1997 blockbuster Face/Off and much more.
Recently, researchers from Bar-Ilan University and the Open University of Israel have developed a similar model known as FSGAN for face swapping and re-enactment in images and videos. Face swapping is used to transfer a face from an image source to a target image while face reenacting or face puppeteering uses the facial movements and expression deformations of a control face in one video to guide the motions and deformations of a face which is appearing in another video.
Behind the Model
The above image shows the overview of Face Swapping GAN or FSGAN which mainly consists of three main components mentioned below:
- Reenactment And Segmentation Generator: This component estimates the reenacted face, its segmentation and estimates the face and hair segmentation mask of the target image
- Face Inpainting Network: This component is used to estimate the missing pixels in the face part. It inpaints the missing parts of the reenacted face based on the face and hair segmentation mask to estimate the complete reenacted face.
- Blending of the Completed Face: The blending generator blends the complete reenacted face and the target’s face using the segmentation mask
Dataset Used
In order to train the generator, video sequences of the IJB-C dataset are used. IJB-C contains approximately 11k face videos of which only 5,500 were used for the training purpose that are in high definition.
Key Takeaways
FSGAN is a deep learning-based approach which can be applied to different subjects without requiring subject-specific training.
The key takeaways of this model are:
- Subject Agnostic Swapping And Reenactment: This model is able to simultaneously manipulate pose, expression and identity without requiring person-specific or pair-specific training while producing high quality and temporally coherent results
- Multiple View Interpolation: This model has the capability of interpolating between multiple views of the same face in a continuous manner based on reenactment
- New Loss Functions: Two new loss functions have been proposed which include a stepwise consistency loss for training face reenactment progressively in small steps, and a Poisson blending loss to train the face blending network to seamlessly integrate the source face into its new context
Limitation of This Model
- This model faces few limitations such as the larger the angular differences, the more identity and texture quality degrades
- Also, too many iterations of the face reenactment generator may lead to blurring the texture of the image
- This method is limited to the resolution of the training data
- Another limitation arises from using a sparse landmark tracking method which fails to fully capture the complexity of facial expressions
Outlook
The proposed model has outperformed several existing face-swapping works without any explicit training on subject-specific images. Due to a number of interactive reasons, General Adversarial Network (GAN) has been successfully used for face manipulating tasks such as generating realistic images of fake faces. However, these methods have both good and the bad side. The researchers of this novel project stated that this method is basically introduced to take measures on various privacy concerns such as face de-identification, face-swapping in images, etc. Applications like face swapping and face reenactment are attracting significant research attention due to their applications in various domains such as in entertainment for visual media production, graphics, pattern recognition, in privacy for photorealistic face de-identification, exchanging faces in images, among others.
Read the paper here.
Share
A Technical Journalist who loves writing about Machine Learning and Artificial Intelligence. A lover of music, writing and learning something out of the box.
Related Posts
Top 10 Most Famous Deepfake AI Tools in 2024
Gopika Raj26/04/2024
Reid Hoffman Creates a DeepFake of Himself, Reid AI
Gopika Raj25/04/2024
Banks are Working on Tech to Counter Deepfakes
Pritam Bordoloi30/01/2024
World ID 2.0 is the Solution for a lot of Deep Fake Scams
Mohit Pandey14/12/2023
8 Deep Tech Companies to Fight against Deepfake
Vandana Nair06/12/2023
Why Focus on Future AI Regulations When Deepfake Crimes Persist?
Vandana Nair26/09/2023
Friend or Fraud?
Shyam Nandan Upadhyay05/09/2023
Deepfakes Are Elevating Meme Culture, But At What Cost?
Anirudh VK18/03/2023
CORPORATE TRAINING PROGRAMS ON GENERATIVE AI
Generative AI Skilling for Enterprises
Our customized corporate training program on Generative AI provides a unique opportunity to empower, retain, and advance your talent.
Indian AI Researchers Should Move Beyond PhDs
Mohit Pandey
Many of the AI researchers just focus on their thesis as the final project, and it dies there.
Gopika Raj
Meet the Young Indian Founders Building AI Products for the World
Sukriti Gupta
Top Editorial Picks
Databricks Acquires Data Management Startup Tabular for Over $1 Billion
Shyam Nandan Upadhyay
Jio Backed Startup TWO AI Unveils ChatSUTRA, India’s Answer to ChatGPT
Siddharth Jindal
Microsoft Introduces AI Weather Forecasting Model ‘Aurora’
Vidyashree Srinivas
Embracing Future-proof AI: Nandan Nilekani’s Vision for Businesses
Anshul Vipat
Microsoft Announces $3.2B Investment To Expand Cloud and AI Infrastructure in Sweden
Gopika Raj
Intel Finally Unveils Lunar Lake AI Chip for Copilot+ PC
Mohit Pandey
Snowflake, NVIDIA Join Forces to Enhance Custom AI Applications
Mohit Pandey
Subscribe to The Belamy: Our Weekly Newsletter
Biggest AI stories, delivered to your inbox every week.
Flagship Events
Rising 2024 | DE&I in Tech Summit
April 4 and 5, 2024 | 📍 Hilton Convention Center, Manyata Tech Park, Bangalore
Data Engineering Summit 2024
May 30 and 31, 2024 | 📍 Bangalore, India
MachineCon USA 2024
26 July 2024 | 583 Park Avenue, New York
Cypher India 2024
September 25-27, 2024 | 📍Bangalore, India
Cypher USA 2024
Nov 21-22 2024 | 📍Santa Clara Convention Center, California, USA
MachineCon GCC Summit 2024
June 28 2024 | 📍Bangalore, India
AI Forum for India
Our Discord Community for AI Ecosystem, In collaboration withNVIDIA.
GenAI
Corner
View All
Zendesk Expects $3 Bn in Revenue From AI by 2027
Ola will Save INR 15 Crore Annually Using Krutrim AI Cloud
Ola Chief Bhavish Aggarwal Meets Arm CEO in Taiwan to Build AI Chips
Snowflake Unveils Polaris Catalog, a Vendor-Neutral, Open Catalog Implementation for Apache Iceberg
India Leads APAC in Data Centre Expansion; Surpasses Japan, Singapore
OpenAI’s GPT-4 Shows Prowess in Picking Stocks
Soon, LLMs Can Help Humans Communicate with Animals