循环一致性调优用于分层图像分解
Cycle-Consistent Tuning for Layered Image Decomposition
利用扩散基础模型和低秩适配进行图层分解，循环一致性训练策略可推广到其他图像分离任务；渐进自改进过程为数据增强提供新思路。
原文依据 we present an in-context image decomposition framework that leverages large diffusion foundation models for layered separation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在视觉和图形学中，解耦真实世界图像中的视觉图层一直是一项持续挑战，因为这些图层通常涉及非线性和全局耦合的交互，包括阴影、反射和透视畸变。在本工作中，我们提出了一种上下文图像分解框架，利用大型扩散基础模型进行分层分离。我们聚焦于具有挑战性的标志-物体分解案例，目标是将标志从其出现的表面上解耦，同时忠实保留两个图层。我们的方法通过轻量级低秩适配微调预训练的扩散模型，并引入循环一致性调优策略，联合训练分解和合成模型，强制分解图像与重组图像之间的重建一致性。这种双向监督显著增强了在图层呈现复杂交互情况下的鲁棒性。此外，我们引入了一种渐进自改进过程，通过迭代地用高质量的模型生成样本增强训练集来精炼性能。大量实验表明，我们的方法实现了准确且连贯的分解，并且能有效泛化到其他分解类型，表明其作为分层图像分解统一框架的潜力。
英文原文摘要 1366 字符
Disentangling visual layers in real-world images is a persistent challenge in vision and graphics, as such layers often involve non-linear and globally coupled interactions, including shading, reflection, and perspective distortion. In this work, we present an in-context image decomposition framework that leverages large diffusion foundation models for layered separation. We focus on the challenging case of logo-object decomposition, where the goal is to disentangle a logo from the surface on which it appears while faithfully preserving both layers. Our method fine-tunes a pretrained diffusion model via lightweight LoRA adaptation and introduces a cycle-consistent tuning strategy that jointly trains decomposition and composition models, enforcing reconstruction consistency between decomposed and recomposed images. This bidirectional supervision substantially enhances robustness in cases where the layers exhibit complex interactions. Furthermore, we introduce a progressive self-improving process, which iteratively augments the training set with high-quality model-generated examples to refine performance. Extensive experiments demonstrate that our approach achieves accurate and coherent decompositions and also generalizes effectively across other decomposition types, suggesting its potential as a unified framework for layered image decomposition.