Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

FlowSteer: Conditioning Flow Field for Consistent Image Restoration

About

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.

Tharindu Wickremasinghe, Chenyang Qi, Harshana Weligampola, Zhengzhong Tu, Stanley H. Chan• 2025

Related benchmarks

TaskDatasetResultRank
DeblurringImage Restoration Benchmark
PSNR32.8749
7
DenoisingImage Restoration Benchmark
PSNR32.2125
7
Super-ResolutionImage Restoration Benchmark
PSNR32.8552
7
ColorizationImage Restoration Benchmark
PSNR27.4214
6
Showing 4 of 4 rows

Other info

Follow for update