Improving Image-to-Image Translation via a Rectified Flow Reformulation

TL;DR

This paper introduces I2I-RFR, a simple plug-in reformulation for image-to-image translation that enhances results by enabling continuous-time refinement without complex generative models.

Contribution

It presents a novel rectified flow reformulation that improves standard I2I regression networks with minimal modifications and inference steps.

Findings

Improves perceptual quality and detail preservation in I2I tasks.

Requires only expanding input channels and a few solver steps at inference.

Consistently outperforms baseline methods across multiple tasks.

Abstract

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.