Plug-and-Play Image Restoration with Flow Matching: A Continuous Viewpoint
By: Fan Jia , Yuhao Huang , Shih-Hsin Wang and more
Potential Business Impact:
Makes blurry pictures sharp and clear.
Flow matching-based generative models have been integrated into the plug-and-play image restoration framework, and the resulting plug-and-play flow matching (PnP-Flow) model has achieved some remarkable empirical success for image restoration. However, the theoretical understanding of PnP-Flow lags its empirical success. In this paper, we derive a continuous limit for PnP-Flow, resulting in a stochastic differential equation (SDE) surrogate model of PnP-Flow. The SDE model provides two particular insights to improve PnP-Flow for image restoration: (1) It enables us to quantify the error for image restoration, informing us to improve step scheduling and regularize the Lipschitz constant of the neural network-parameterized vector field for error reduction. (2) It informs us to accelerate off-the-shelf PnP-Flow models via extrapolation, resulting in a rescaled version of the proposed SDE model. We validate the efficacy of the SDE-informed improved PnP-Flow using several benchmark tasks, including image denoising, deblurring, super-resolution, and inpainting. Numerical results show that our method significantly outperforms the baseline PnP-Flow and other state-of-the-art approaches, achieving superior performance across evaluation metrics.
Similar Papers
Image Restoration via Primal Dual Hybrid Gradient and Flow Generative Model
CV and Pattern Recognition
Cleans up blurry or noisy pictures better.
Physics-Informed Image Restoration via Progressive PDE Integration
CV and Pattern Recognition
Cleans up blurry photos using math.
Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projection
CV and Pattern Recognition
Improves blurry pictures by combining math and AI.