通过修正流重新公式化改进图像到图像转换
Improving Image-to-Image Translation via a Rectified Flow Reformulation
AI总结：
本文提出I2I-RFR方法，通过将标准图像到图像回归网络重新解释为连续时间传输模型，提升图像转换性能，保留传统监督训练流程，增强感知质量和细节保留。
摘要：
在本工作中，我们提出图像到图像修正流重新公式化（I2I-RFR），一种实用的插件重新公式化方法，将标准图像到图像回归网络重新解释为连续时间传输模型。尽管像素级图像到图像回归简单、稳定且易于适应不同任务，但往往过度平滑了不明确的多模态目标，而生成式替代方法通常需要额外组件、任务特定调优和更复杂的训练和推理流程。我们的方法通过通道拼接将骨干输入与噪声污染的真实目标版本相结合，并优化简单的t加权像素损失。该目标通过诱导速度场获得修正流解释，使推理时间能够基于ODE进行逐步细化，同时在很大程度上保留标准监督训练流程。在大多数情况下，采用I2I-RFR只需扩展输入通道，推理可通过少量显式求解器步骤（例如3步）完成，无需蒸馏。在多个图像到图像转换和视频修复任务中进行的广泛实验表明，I2I-RFR在广泛的任务和骨干网络中普遍提升了性能，特别是在感知质量和细节保留方面有明显提升。总体而言，I2I-RFR提供了一种轻量级方法，将连续时间细化纳入传统I2I模型，而无需要求重型生成流程。
英文摘要：
In this work, we propose Image-to-Image Rectified Flow Reformulation (I2I-RFR), a practical plug-in reformulation that recasts standard I2I regression networks as continuous-time transport models. While pixel-wise I2I regression is simple, stable, and easy to adapt across tasks, it often over-smooths ill-posed and multimodal targets, whereas generative alternatives often require additional components, task-specific tuning, and more complex training and inference pipelines. Our method augments the backbone input by channel-wise concatenation with a noise-corrupted version of the ground-truth target and optimizes a simple t-reweighted pixel loss. This objective admits a rectified-flow interpretation via an induced velocity field, enabling ODE-based progressive refinement at inference time while largely preserving the standard supervised training pipeline. In most cases, adopting I2I-RFR requires only expanding the input channels, and inference can be performed with a few explicit solver steps (e.g., 3 steps) without distillation. Extensive experiments across multiple image-to-image translation and video restoration tasks show that I2I-RFR generally improves performance across a wide range of tasks and backbones, with particularly clear gains in perceptual quality and detail preservation. Overall, I2I-RFR provides a lightweight way to incorporate continuous-time refinement into conventional I2I models without requiring a heavy generative pipeline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
