让流模型一步生成条件图像，通过学习初始噪声实现精准控制。
Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
- 将条件生成转为学习合适的初始噪声分布。
- 在ImageNet上采样速度提升数量级，质量媲美迭代模型。
- 适合需要快速生成且精度要求高的逆问题场景。
流模型可在单次前向传播中生成高质量图像，但缺乏显式的采样轨迹，难以融入外部约束进行条件生成或解决逆问题。本文提出变分流映射（Variational Flow Maps, VFM），将条件生成的视角从‘引导采样路径’转变为‘学习恰当的初始噪声’。给定观测数据，通过训练噪声适配器模型输出噪声分布，使经流映射到数据空间后的样本既满足观测又符合数据先验。为此，我们设计了一个合理的变分目标，联合训练噪声适配器与流模型，增强噪声与数据的对齐性，从而仅用一个（或少数）步骤即可实现复杂数据后验的采样。在多种逆问题上的实验表明，VFM能生成校准良好的条件样本；在ImageNet上，其生成质量与迭代扩散/流模型相当，但采样速度提升数量级。代码已公开于https://github.com/abbasmammadov/VFM。
原文摘要 · Abstract (English)
Flow maps enable high-quality image generation in a single forward pass. However, unlike iterative diffusion models, their lack of an explicit sampling trajectory impedes incorporating external constraints for conditional generation and solving inverse problems. We put forth Variational Flow Maps, a framework for conditional sampling that shifts the perspective of conditioning from "guiding a sampling path", to that of "learning the proper initial noise". Specifically, given an observation, we seek to learn a noise adapter model that outputs a noise distribution, so that after mapping to the data space via flow map, the samples respect the observation and data prior. To this end, we develop a principled variational objective that jointly trains the noise adapter and the flow map, improving noise-data alignment, such that sampling from complex data posterior is achieved with a simple adapter. Experiments on various inverse problems show that VFMs produce well-calibrated conditional samples in a single (or few) steps. For ImageNet, VFM attains competitive fidelity while accelerating the sampling by orders of magnitude compared to alternative iterative diffusion/flow models. Code is available at https://github.com/abbasmammadov/VFM
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。