用视觉语言模型评分优化图像分层模型，无需成对标注。
Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
- 通过VLM评分生成奖励信号，用强化学习微调分层模型。
- 在Crello数据集上层间分离度更强，伪影更少，重建误差更低。
- 适合做图像编辑、可解释性分析的研究者参考。
我们提出Stable-Layers，一个无需成对监督的强化学习框架，通过视觉语言模型（VLM）反馈微调预训练图像分层模型。基于Qwen-Image-Layered，采用Flow-GRPO结合LoRA适配，对每张图像采样多个候选分解，由VLM评分后，基于组内相对优势优化策略。关键挑战在于：VLM单独评分易压缩判断至狭窄区间，导致组内差异过小。为此，我们设计双阶段评估流程：先按五项编辑核心标准逐样本评分，再通过网格化校准步骤让VLM并列重评所有候选。相比基线模型，Stable-Layers在Crello数据集上实现更强的层间分离、更少空白或伪影层，且每层重建误差更低。
原文摘要 · Abstract (English)
We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using only feedback from a vision-language model (VLM). Starting from Qwen-Image-Layered, we apply Flow-GRPO with LoRA adaptation, sampling multiple candidate decompositions per image, scoring them with a VLM, and optimising the policy from group-relative advantages. The key challenge lies in designing a reliable reward signal: VLMs scoring samples in isolation tend to compress their judgements into a narrow band, leaving GRPO with little within-group variance to learn from. We address this with a two-stage evaluation pipeline that pairs structured per-sample scoring across five edit-centric criteria with a grid-based calibration step in which the VLM re-scores all candidates side-by-side. Stable-Layers produces decompositions with stronger layer separation, fewer blank or artifact-heavy layers, and lower per-layer reconstruction error on the Crello dataset compared to the base model.
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。