Lipschitz-Controlled Flow Matching 如何提升圖像復原的穩定性
Lipschitz-Controlled Flow Matching for Robust Image Restoration
LipsFlower 結合 Lipschitz 感知架構與正則化,減少流匹配圖像復原中的輸入擾動放大,同時維持具競爭力的復原品質。其向量場架構 LipHDiT 採用穩定化近似頻譜正規化、有界調制及凸殘差混合,並以有限半徑對抗增益正則化抑制過度敏感。盲人臉部復原測試顯示,LipsFlower 在維持復原品質的同時降低擾動放大。
Published on Nov 10
Authors:
,
,
Abstract
LipsFlower stabilizes flow-matching image restoration by combining Lipschitz-aware architecture and regularization to reduce perturbation amplification while maintaining competitive restoration quality.
Flow-matching models can produce high-quality image restorations, but their learned dynamics may amplify small input perturbations and make reconstructions unstable. We introduce LipsFlower to reduce this amplification. We derive stability bounds for Flow-from-Y, which initializes the ordinary differential equation from a noise-perturbed observation, as well as for observation-conditioned posterior sampling, which conditions the velocity field on the observation throughout integration. Based on this analysis, we develop LipHDiT, a Lipschitz-aware hourglass diffusion transformer that serves as the vector-field architecture of LipsFlower. LipHDiT incorporates stabilized approximate spectral normalization, bounded modulation, and convex residual mixing. We also use adversarial finite-radius gain regularization at sampled interpolation states to penalize excessive sensitivity to the state and, for conditional sampling, the observation. We test both formulations on blind face restoration, measuring adversarial robustness and the perceptual quality of the reconstructions. LipsFlower reduces perturbation amplification while keeping restoration quality competitive with the evaluated baselines. These results suggest that Lipschitz-aware flow matching can improve the stability of generative image restoration.
View arXiv page View PDF Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.13995 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.13995 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.13995 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co