Machine Learning for Graphics and Computer Vision Advanced Learning Path - MAI4CAREU Master in AI

This Machine Learning for Graphics and Vision Learning path offers a carefully crafted curriculum that merges the realms of computer vision and computer graphics, key areas in artificial intelligence that are transforming technology and creative industries. It is designed for the Master's program in Artificial Intelligence of the University of Cyprus, which was developed with co-funding from the MAI4CAREU European project. The course provides an in-depth exploration of both theoretical and practical aspects. Over 13 weeks, this course covers essential topics such as basic regression, deep learning for image and video analysis, feature extraction, semantic understanding, and creative applications like style transfer. Additionally, it delves into the intersection of vision and graphics, exploring 3D data processing, generative networks, motion capture, and neural rendering. The curriculum is structured to progressively build students' expertise, starting with foundational concepts, and advancing to sophisticated techniques, preparing them to tackle real-world challenges and innovate in the field of graphics and vision.

Part I: Introduction

1.Overview of machine learning and introduction to basic regression techniques

• Supervised, unsupervised, and reinforcement learning
• Understanding linearity and non-linearity in machine learning models

Part II: Computer Vision

2. Fundamentals of Computer Vision

• Image formation and representation
• Basic image processing techniques
• Feature detection and matching

3. Machine Learning for Image Recognition  

• Convolutional Neural Networks (CNNs)
• Transfer learning and fine-tuning
• Object detection and segmentation

4. Deep Learning for Computer Vision

• Deep learning techniques for image classification
• advanced CNN architectures: ResNet, Inception, DenseNet
• Object detection algorithms such as YOLO and Faster R-CNN

5. Deep Learning for Videos

• Deep learning approaches for video classification

6. Semantic Understanding

• Deep learning for semantic segmentation
• Visualize and interpret neural network layers and activations
• Generative Adversarial Networks (GANs) and their applications
• Image inpainting and saliency detection using GANs
• Autoencoders and their use in image denoising and generation

Part III: Computer Graphics

7. Machine Learning in Computer Graphics

• Graphics pipelines and rendering techniques.
• Compositional image generation techniques.
• Style transfer and neural texture synthesis.

8. 3D Computer Vision  

• 3D reconstruction and depth estimation.
• Point clouds and 3D mesh processing.
• Processing irregular data structures.
• Applications of deep learning in 3D vision.

9. Character Animation

• Motion capture techniques, pose representation, and character animation.
• Human Pose Estimation and Activity Recognition
  • Keypoint detection and tracking
  • Skeleton-based action recognition
  • Applications in sports, healthcare, and entertainment
• Deep motion analysis and synthesis
• Deep reinforcement learning for animation control and physics-based animation.

Part IV: Advanced Topics in Graphics and Vision

10. Advanced Topics

• Neural style transfer
• Texture synthesis.
• Neural rendering techniques to create realistic images.
• Image and video super-resolution
• Creative Applications
  • Generative networks for creating faces, landscapes, and sketches.
  • Denoising techniques in image processing.
  • Adversarial training and open research problems.