Core Research Specialization

Generative AI

Generative models including GANs, VAEs, and Diffusion Models for image synthesis and manipulation.

1 Researchers 1 Projects 1 Publications

Collaborate in this Area Join Research Lab

In-Depth Overview

Research Focus & Scope

Generative AI research at ICVRL explores the frontier of synthetic data creation, image synthesis, neural rendering, and multi-modal generative modeling. We harness generative architectures to solve extreme data scarcity in scientific domains and pioneer new visual creativity tools.

Methodological Approach

How We Conduct Research in Generative AI

Our focus covers Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Latent Diffusion Models, and Neural Radiance Fields (NeRFs). We specialize in conditional image generation, super-resolution, synthetic medical dataset creation, and domain translation.

Impact & Deployments

Real-World Applications

Medical dataset synthesis for rare condition training

High-fidelity super-resolution and image restoration

Text-to-image and sketch-to-photo synthesis

Virtual environments and 3D NeRF reconstruction

Privacy-preserving synthetic dataset generation

Lab Projects

Projects in this Domain

All Projects

SynMed: Synthetic Medical Data Generation Framework

A GAN-based framework for generating high-fidelity synthetic medical images to address data scarcity in health...

completed Code

Scholarly Output

Recent Publications

All Publications

journal

GAN-Based Synthetic Data Augmentation for Rare Disease Classification

Muhammad Hamza, Shams ur Rehman, Ayesha Malik

Medical Image Analysis, 2024

Tech Stack & Tools

Stable Diffusion ControlNet StyleGAN3 NeRF PyTorch Diffusers Accelerate CUDA

Active Researchers

Muhammad Hamza

PhD Researcher

View All Researchers

Join Our Research

Interested in conducting MS/PhD research or undergraduate projects in Generative AI?

Apply to Join ICVRL

More Domains

Explore Other Research Areas

All Areas