Iterative Flow Matching -- Path Correction and Gradual Refinement for Enhanced Generative Modeling
Journal:
arXiv
Published Date:
Feb 23, 2025
Abstract
Generative models for image generation are now commonly used for a wide
variety of applications, ranging from guided image generation for entertainment
to solving inverse problems. Nonetheless, training a generator is a non-trivial
feat that requires fine-tuning and can lead to so-called hallucinations, that
is, the generation of images that are unrealistic. In this work, we explore
image generation using flow matching. We explain and demonstrate why flow
matching can generate hallucinations, and propose an iterative process to
improve the generation process. Our iterative process can be integrated into
virtually $\textit{any}$ generative modeling technique, thereby enhancing the
performance and robustness of image synthesis systems.
