Style Transfer of High-resolution Photos to Artworks

Type: MA thesis

Status: running

Supervisors: Aline Sindel

Aim of the thesis is the generation of artistic images, such as paintings, prints or drawings, from high-resolution photos which preserve the fine details of the foreground objects. Style transfer methods using diffusion models and classical CNNs shall be implemented for this task.

Requirements:

  • Implementation in PyTorch
  • Experience and theoretical knowledge in the area of Deep Learning, Pattern Recognition, Computer Vision, and Image Processing
  • Target study programme: Computer Science or related

In case you are interested in the topic, then please send me (@ Aline) an email with your CV and transcript of records.