FlowSteer: Conditioning Flow Field for Consistent Image Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wickremasinghe, Tharindu, Qi, Chenyang, Weligampola, Harshana, Tu, Zhengzhong, Chan, Stanley H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913160852668416
author Wickremasinghe, Tharindu
Qi, Chenyang
Weligampola, Harshana
Tu, Zhengzhong
Chan, Stanley H.
author_facet Wickremasinghe, Tharindu
Qi, Chenyang
Weligampola, Harshana
Tu, Zhengzhong
Chan, Stanley H.
contents 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. All data and code will be publicly available \href{https://tharindu-nirmal.github.io/FlowSteer/}{in this link}.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlowSteer: Conditioning Flow Field for Consistent Image Restoration
Wickremasinghe, Tharindu
Qi, Chenyang
Weligampola, Harshana
Tu, Zhengzhong
Chan, Stanley H.
Image and Video Processing
Computer Vision and Pattern Recognition
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. All data and code will be publicly available \href{https://tharindu-nirmal.github.io/FlowSteer/}{in this link}.
title FlowSteer: Conditioning Flow Field for Consistent Image Restoration
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.08125