Universität Bielefeld Play

[MA]

Diffusion Models for Virtual Try-On under Domain Shift: A Multi-Dataset Perspective

Contact: Riza Velioglu - Petra Bevandic

This project investigates the intersection of multi-dataset training, domain shifts, and generalization in the context of image-to-image diffusion models for Virtual Try-Off (VTOFF) task. It aims to understand how training on diverse datasets affects the performance and robustness of such models across different domains.

Key research questions include:

Example tasks include:

Literature