FlowSteer: Conditioning Flow Field for Consistent Image Restoration
This addresses the challenge of efficiently leveraging generative models for image restoration without task-specific retraining, though it is incremental as it builds on existing flow models.
The paper tackles the problem of image restoration using flow-based text-to-image models, which often drift from faithful measurements, by introducing FlowSteer, a conditioning scheme that improves measurement consistency and identity preservation in a zero-shot setting across tasks like super-resolution and deblurring.
Flow-based text-to-image (T2I) models excel at prompt-driven image generation, but falter on Image Restoration (IR), often "drifting away" from being faithful to the measurement. Prior work mitigate this drift with data-specific flows or task-specific adapters that are computationally heavy and not scalable across tasks. This raises the question "Can't we efficiently manipulate the existing generative capabilities of a flow model?" To this end, we introduce FlowSteer (FS), an operator-aware conditioning scheme that injects measurement priors along the sampling path,coupling a frozed flow's implicit guidance with explicit measurement constraints. Across super-resolution, deblurring, denoising, and colorization, FS improves measurement consistency and identity preservation in a strictly zero-shot setting-no retrained models, no adapters. We show how the nature of flow models and their sensitivities to noise inform the design of such a scheduler. FlowSteer, although simple, achieves a higher fidelity of reconstructed images, while leveraging the rich generative priors of flow models.