BiFM：面向少步图像编辑与生成的双向流匹配
BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation
把「图像→噪声」的反演方向也纳入流匹配训练，用共享瞬时速度场与连续时间区间监督实现单步反演，可直接替换现有少步编辑管线中的反演模块，提升少步采样下的编辑保真度。
原文依据 BiFM directly estimates average velocity fields in both "image \to noise" and "noise \to image" directions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期的扩散模型与流匹配模型通过迭代采样逐步去噪，在图像生成与编辑上展现出强大能力。虽然这使得保持语义的编辑可以进行灵活反演，但少步采样情形下的前向过程近似较差，导致编辑质量下降。现有的少步反演方法往往依赖预训练生成器和辅助模块，限制了可扩展性以及在不同架构间的泛化能力。为解决这些局限，我们提出 BiFM（双向流匹配），这是一个在单一模型内联合学习生成与反演的统一框架。BiFM 直接估计「图像→噪声」与「噪声→图像」两个方向上的平均速度场，并由一个共享的瞬时速度场加以约束，该瞬时速度场来自预定义调度或预训练的多步扩散模型。此外，BiFM 引入了一种使用连续时间区间监督的新训练策略，并由双向一致性目标与轻量的时间区间嵌入加以稳定。这种双向形式还支持单步反演，并可无缝集成到主流的扩散与流匹配骨干网络中。在多种图像编辑与生成任务上，BiFM 一致优于现有的少步方法，取得了更优的性能与可编辑性。代码与模型将在论文被接收后发布。
英文原文摘要 1478 字符
Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits, few-step sampling regimes suffer from poor forward process approximation, leading to degraded editing quality. Existing few-step inversion methods often rely on pretrained generators and auxiliary modules, limiting scalability and generalization across different architectures.To address these limitations, we propose BiFM (Bidirectional Flow Matching), a unified framework that jointly learns generation and inversion within a single model. BiFM directly estimates average velocity fields in both "image \to noise" and "noise \to image" directions, constrained by a shared instantaneous velocity field derived from either predefined schedules or pretrained multi-step diffusion models. Additionally, BiFM introduces a novel training strategy using continuous time-interval supervision, stabilized by a bidirectional consistency objective and a lightweight time-interval embedding. This bidirectional formulation also enables one-step inversion and can integrate seamlessly into popular diffusion and flow matching backbones.Across diverse image editing and generation tasks, BiFM consistently outperforms existing few-step approaches, achieving superior performance and editability. Our code and models will be released upon acceptance.