Computer Vision

• 2D/3D Scene Understanding
• Object Detection, Tracking & Recognition
• Motion and Video Analytics
• Action and Activity Recognition
• Vision-Language Models, Multimodal Learning
• Self-supervised, Few-shot and Zero-shot Vision
• Adversarial and Explainable Vision Systems
• Human-Computer Interaction and Gesture Recognition

Image Processing

• Image Restoration, Enhancement & Super-Resolution
• Image/Video Compression and Coding
• Medical & Biomedical Image Analysis
• Remote Sensing and Satellite Image Interpretation
• Hyperspectral and Multispectral Image Processing
• Image Segmentation, Morphology & Statistical Approaches
• Visual Cryptography, Steganography & Security

Graphics & Visualization

• 3D Modelling, Reconstruction & Rendering
• Animation, Simulation & Visual Effects
• Virtual Reality, Augmented Reality & Mixed Reality
• View Synthesis and Image-based Rendering
• Computational Photography

Pattern Recognition & Machine Learning

• Deep Learning Architectures for Vision
• Representation Learning
• Vision Transformers & Diffusion Models
• Graph Neural Networks and Geometric ML
• Reinforcement Learning for Vision
• Vision-based Robotics and Autonomous Systems

Emerging Areas

• Agentic AI for Vision and Graphics
• Vision-Language Models (VLMs) and Multimodal Foundation Models
• Trustworthy, Ethical and Robust Vision Systems
• AI for Remote Sensing and Large-Scale Societal Applications
• AI for Accessibility and Assistive Vision Technologies
• Neuromorphic and Event-based Vision Systems
• VLSI and Hardware Acceleration for Vision & Graphics
• Vision for Creative Media, AR/VR/MR and Interactive Intelligence