Iterative Flow Matching -- Path Correction and Gradual Refinement for Enhanced Generative Modeling
This addresses hallucinations in image generation for applications like entertainment and inverse problems, but appears incremental as it builds on existing flow matching techniques.
The paper tackles the problem of hallucinations in generative image models by analyzing flow matching and proposing an iterative correction process. The result is a method that can be integrated into any generative modeling technique to enhance performance and robustness.
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.