Solving Inverse Problems with Flow-based Models via Model Predictive Control
Researchers have developed MPC-Flow, a novel framework for solving inverse problems using flow-based generative models. This method employs model predictive control to guide the model's dynamics, making conditional generation more practical. MPC-Flow offers a spectrum of guidance algorithms, some of which bypass the need for backpropagation through the generative model's trajectory. The framework has demonstrated strong performance and scalability on image restoration tasks, including in-painting, deblurring, and super-resolution, even with large-scale models like FLUX.2 on consumer hardware. AI
IMPACT Introduces a more efficient method for conditional generation in flow-based models, potentially improving performance on tasks like image restoration.