FlowSteer: Conditioning Flow Field for Consistent Image Restoration

TL;DR

FlowSteer is a novel operator-aware conditioning method that enhances flow-based image restoration tasks by injecting measurement priors during sampling, improving fidelity without retraining or adapters.

Contribution

FlowSteer introduces a simple, zero-shot conditioning scheme for flow models that improves image restoration quality across multiple tasks without additional training.

Findings

Increases measurement consistency in restored images

Enhances identity preservation in image restoration

Operates effectively without retraining or adapters

Abstract

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.