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.
Unsupervised Layered Image Decomposition into Object Prototypes
LIGM, École des Ponts, Univ Gustave Eiffel, CNRS(LIGM,巴黎高科路桥学校,古斯塔夫·埃菲尔大学,法国国家科学研究中心);Inria and DIENS (ENS-PSL, CNRS, Inria)(法国国家信息与自动化研究所和DIENS(巴黎高等师范学院-巴黎文理研究大学,法国国家科学研究中心,法国国家信息与自动化研究所));Center for Data Science, New York University(纽约大学数据科学中心)