Controlling the Style of Images Generated using StyleGAN

Generative adversarial networks (GANs) are algorithmic architectures that use two neural networks, pitting one against the other (thus the “adversarial”) in order to generate new, synthetic instances of data that can pass for real data. They are used widely in image generation, video generation and voice generation

While GAN images become more realistic over time,one of the main challenges is controlling the output i.e:changing specific features such as pose,face shape and hair style. NVIDIA proposed a novel method which generated images starting from very low resolution and continuing to high resolution.By modifying the input at each level,it controls the visual features in that level from coarse features(pose,face shape) to find details(hair color without affecting other levels)

In this talk,I will be discussing how the lack of control affected the generation of images in previous GAN models and the changes introduced by StyleGAN that help in controlling the style and generating impressive images of synthetic human faces

 
 

Outline/Structure of the Demonstration

Agenda for the talk:

  • Recap of GAN( 2 mins)
  • Use cases of StyleGAN( 2 mins )
  • StyleGAN Architecture( 10 mins)
  • Code walkthrough: Image Generation with StyleGAN( 4 mins )
  • Q / A session ( 2mins )

Learning Outcome

1.Why StyleGAN is a major breakthrough in the field of GAN

2.How it is used in Real life scenarios

3.Good understanding of the StyleGAN Architecture

Target Audience

Data Scientist, Deep Learning Engineers, Computer Vision Engineer, AI Researchers

Prerequisites for Attendees

Attendees are required to have a good understanding of basic ML and DL especially Convolutional Neural Networks and Generative Adversarial Networks

schedule Submitted 4 months ago

Public Feedback

comment Suggest improvements to the Speaker
  • Deepti Tomar
    By Deepti Tomar  ~  3 months ago
    reply Reply

    Hello Gouthaman,

    Could you give more details on the real-world implementation of the techniques mentioned in the outline/structure? Have you already applied the techniques in a specific industry/domain/field?

    Thanks,

    Deepti

    • Gouthaman Asokan
      By Gouthaman Asokan  ~  3 months ago
      reply Reply

      Hi Deepti,
      I have done the mentioned project for Cellstrat AI Lab,one of the leading R&D Organiation to innvoate AI.It helps in creating high quality and realistic images,also having the control over the generated images.Understanding this will be a key step in fighting against Deepfake AI.
      Thanks,
      Gouthaman

  • Natasha Rodrigues
    By Natasha Rodrigues  ~  4 months ago
    reply Reply

    Hi Gouthaman,

    Thanks for your proposal and for your voice-over videos, however to help the program committee understand your presentation style, can you provide a link to your past recording or record a small 1-2 mins trailer of your talk and share the link to the same?

    Thanks,

    Natasha


  • Liked Gouthaman Asokan
    keyboard_arrow_down

    Gouthaman Asokan - Real Time Multi Person Pose Estimation

    Gouthaman Asokan
    Gouthaman Asokan
    AI Researcher
    Cellstrat
    schedule 4 months ago
    Sold Out!
    20 Mins
    Demonstration
    Intermediate

    Openpose is a library written in C++ with python wrapper available for real time multi person key point detection and multithreading. This model predicts the location of various human keypoints such as chest, hips, shoulder, neck, elbows, knees. This model uses part affinity fields and greedy inference to connect these localized keypoints.

    In this talk, I'll be discussing how Openpose helps in the real time multi person detection system to jointly detect human body,hand,facial and foot keypoints detection and the part affinity field.

    Also,discuss the model architecture,comparing with other models like Mask RCNN and AlphaPose. Finally show how pose estimation can be done on single as well as multiple person images using pretrained models

  • Liked Gouthaman Asokan
    keyboard_arrow_down

    Gouthaman Asokan - Proximal Policy Optimization: OpenAI's Major Breakthrough

    Gouthaman Asokan
    Gouthaman Asokan
    AI Researcher
    Cellstrat
    schedule 4 months ago
    Sold Out!
    20 Mins
    Demonstration
    Intermediate

    OpenAI made a breakthrough in Deep Reinforcement Learning when they created OpenAI five,a team of 5 agents and beat some of the best Dota2 players in the world.

    Underlying algorithm that helped them in achieving this is Proximal Policy Optimization.OpenAI told that PPO has become its default reinforcement algorithm because of its ease and good performance.It uses novel policy gradient techniques that was more efficient and less costly than the traditional reinforcement learning methods.Key contribution of PPO is ensuring that a new update of policy does not change it too much from the previous policy.This leads to less variance at the cost of some bias but ensures smoother training.It also makes sure that the agent does not go down the unrecoverable path of taking senseless actions.

    In this talk,I will be discussing the architecture of PPO,its major changes from Policy Gradient methods and how it can be implemented through code