paper-with-me

홈 › Papers

Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration

2026-03-04 · Xiaohui Sun, Hanlin Wu arxiv

Face restoration can be formulated as a continuous-time transformation between image distributions via Flow Matching (FM). However, standard FM typically employs independent coupling, ignoring the statistical correlation between low-quality (LQ) and high-quality (HQ) data. This leads to intersecting trajectories and high velocity-field curvature, requiring multi-step integration. We propose Shortcut-constrained Coupling Flow for Face Restoration (SCFlowFR) to address these challenges. By establishing a data-dependent coupling, we explicitly model the LQ-HQ dependency to minimize path crossovers and promote near-linear probability flow. Furthermore, we employ a conditional mean estimator to refine the source distribution's anchor, effectively tightening the transport cost and stabilizing the velocity field. To ensure stable one-step inference, a shortcut constraint is introduced to supervise average velocities over arbitrary intervals, mitigating discretization bias in large-step updates. SCFlowFR achieves state-of-the-art one-step restoration, providing a superior trade-off between perceptual fidelity and computational efficiency.

📄 PDF Abstract BibTeX arXiv:2603.03648

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

An Online Feedback-Based Linearized Power Flow Model for Unbalanced Distribution Networks

2021-03-27 · Rui Cheng, Zhaoyu Wang, Yifei Guo

The non-linearity and non-convexity of power flow models and the phase coupling challenge the analysis and optimization of unbalanced distribution networks. To tackle the challenges, this paper proposes an online feedbac…

Stochastic dynamical modeling of turbulent flows

2019-08-26 · Armin Zare, Tryphon T. Georgiou, Mihailo R. Jovanović

Advanced measurement techniques and high performance computing have made large data sets available for a wide range of turbulent flows that arise in engineering applications. Drawing on this abundance of data, dynamical …

Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic Systems

2026-07-23 · Akihiro Takemura, Katsumi Inoue arxiv

Neurosymbolic (NeSy) systems integrate neural networks with logical reasoning to achieve both generalization and interpretability, but recent work has shown they are susceptible to shortcut reasoning behaviors. We propos…

Logical Reasoning

Safe Reinforcement Learning with Chance-constrained Model Predictive Control

2021-12-27 · Samuel Pfrommer, Tanmay Gautam, Alec Zhou, Somayeh Sojoudi

Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints. We address the challenge of safe RL by coupling a safety guide based on model predictive co…

Model Predictive Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage training

2025-09-25 · Naisong Zhou, Saisamarth Rajesh Phaye, Milos Cernak, Tijana Stojkovic 외 arxiv

Diffusion-based generative models have achieved state-of-the-art performance for perceptual quality in speech enhancement (SE). However, their iterative nature requires numerous Neural Function Evaluations (NFEs), posing…

Speech Enhancement