FlowBender：针对自修正条件流的基于反馈的训练方法
FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows
摘要
条件性扩散和流模型通常无法满足定义其功能的约束条件。例如，深度条件模型所生成的图像中，重新提取的深度值与输入值不一致，尽管在训练和推理过程中都有用于定义这些约束条件的深度预测器可用。现有的方法大致可以分为两类：一类是监督式模型，它们将条件信号视为静态提示，在推理过程中忽略对齐信息；另一类则是基于引导的方法，它们通过手动调整的线性更新来利用条件信号，通常是以对条件的精确性为代价，换取生成样本的合理性。我们认为，这两种方法的根本问题在于模型从未被训练来利用自身的对齐误差。我们提出了FlowBender这一闭环框架，它将这种误差作为重要输入，让网络根据推理时的反馈来学习修正策略。在每一步中，无引导的前瞻性处理步骤会估计出干净的信号，通过前向算子计算特定任务的偏差，然后进一步处理该信号以得到修正后的速度值。我们还提出了FlowBender的多种变体，包括适用于可微操作器的梯度-Based实现方式，以及适用于不可微场景如JPEG压缩的零阶变体。为了实现高效的采样，我们引入了预步骤捷径机制，从而能够以最小的额外计算成本实现闭环修正。在图像到图像转换、恢复以及3D网格纹理生成等任务中，FlowBender始终优于标准的监督式基准模型、带有对齐损失补偿的训练方法以及最先进的推理时引导技术，同时实现了精确性和合理性的平衡，而不是将其相互取舍。项目页面：https://flow-bender.github.io/
English Abstract
Conditional diffusion and flow models routinely fail to satisfy the very constraints that define their task. For instance, a depth-conditioned model often produces images whose re-extracted depth disagrees with the input, even though the forward operator--the depth predictor defining the constraint--is available during both training and inference. Existing approaches generally fall into two categories: supervised models that treat the conditioning signal as a static cue and ignore alignment information at inference, and guidance-based methods that consult it through hand-tuned linear updates, typically trading fidelity to the condition against the plausibility of the generated sample. We argue that the fundamental gap in both paradigms is that the model is never trained to utilize its own alignment error. We introduce FlowBender, a closed-loop framework that treats this error as a first-class input, training the network to learn a correction policy conditioned on inference-time feedback. At each step, an unguided look-ahead pass estimates the clean signal, a task-specific deviation is computed via the forward operator, and a refinement pass consumes this signal to produce a corrected velocity. We propose several variants of FlowBender, including a gradient-based formulation for differentiable operators and a zero-order variant for non-differentiable settings such as JPEG compression. For efficient sampling, we introduce a prior-step shortcut that enables closed-loop correction at a minimal additional computational cost. Across image-to-image translation, restoration, and 3D mesh texturing, FlowBender consistently outperforms standard supervised baselines, alignment-loss-augmented training, and state-of-the-art inference-time guidance, improving fidelity and plausibility simultaneously rather than trading them against each other. Project page: https://flow-bender.github.io/