AI 中文总结
该研究提出RRFC框架，通过反馈条件实现迭代式图像到图像生成的输出精修，在多类模型和任务上评估发现其增益集中于目标属性重叠的任务。
AI 中文摘要
条件图像到图像生成器是单步的：它们通过一次前向传播将输入特征映射到输出，并将其视为最终结果，没有改进的机会。尽管这类模型经过训练后能在单步内生成尽可能好的结果，但如果能在迭代过程中自适应地修正自身输出，仍有改进空间。我们提出了Recursive Refinement via Feedback Conditioning（RRFC，基于反馈条件的递归精修），这是一种用于迭代输出精修的新型反馈条件框架，它通过对新信号（即模型最近一次的预测结果）进行条件设置，指导模型自适应修正输出；该预测结果会作为辅助通道，与原始输入一同被送入模型。这一设计在保留生成器核心架构的同时，修改了其条件接口，并根据模型家族的不同调整其训练或推理流程，因此RRFC可附加到现有生成器上，无需重新设计。我们在涵盖对抗式、平衡式及扩散式模型的6个基线模型，以及3项配对图像到图像翻译任务上对RRFC进行了评估。在18种架构-任务设置中，RRFC取得了7项经Holm校正的改进、7项性能下降和4项无显著变化。增益集中在重建保真度和身份相关设置中，而7项性能下降中的5项出现在单一语义布局任务上，该任务中所有模型均出现性能下降。这些结果表明，当基于反馈的精修目标与所评估的属性重叠时，它会发挥作用，且其增益集中在重叠成立的任务中。
英文摘要
Conditional image-to-image generators are single-shot: they map input features to an output in one forward pass and treat it as final, with no opportunity to improve on it. Although trained to produce the best possible result in one step, such a model leaves room for improvement if it can adaptively revise its own output over iterations. We propose Recursive Refinement via Feedback Conditioning (RRFC), a novel feedback-conditioning framework for iterative output refinement that teaches a model to adaptively revise its output by conditioning on a new signal, namely its most recent previous prediction, which is fed back as an auxiliary set of channels alongside the original input. This preserves the generator's core architecture while modifying its conditioning interface and, depending on the model family, its training or inference procedure, so RRFC can be attached to existing generators without redesign. We evaluate RRFC across six baselines spanning adversarial, equilibrium, and diffusion-based models and three paired image-to-image translation tasks. Across 18 architecture-task settings, RRFC yields seven Holm-corrected improvements, seven degradations, and four non-significant changes. The gains concentrate on reconstruction-fidelity and identity settings, while five of the seven degradations fall on the single semantic-layout task, where every model declines. These results indicate that feedback-based refinement helps when its objective overlaps with the evaluated property, and that its gains concentrate on the tasks where that overlap holds.
