外观
论文HF Daily Papers · arXiv 2610.2473811 天前
LayerEditor框架实现指令编辑与可复用RGBA图层生成统一
本文由 AI 根据公开内容整理，可能有误，请以原文为准：Editing Images into Reusable Layers via Compositional Edit-Prior Distillation（HF Daily Papers · arXiv 2610.24738）
核心内容
针对现有图像编辑模型输出扁平化、难以局部复用及分解与编辑优化割裂的问题，研究团队提出LayerEditor统一框架。该方案将指令引导的图像编辑与可复用RGBA图层生成耦合，解决了传统方法无法兼顾语义编辑精度与图层显式控制的痛点，为机器人视觉感知与仿真环境构建提供了新的分层表征工具。
技术上采用In-Context RGB-Alpha Token Modeling，在单一令牌序列中联合表示编辑画布与有序RGBA图层；引入Compositional Edit-Prior Distillation策略，将预训练编辑先验迁移至画布及预测图层合成结果，保持编辑保真度。同时构建包含10万对样本的LayerEditor-100K数据集及专用基准，验证了其在多层分解与灵活层级操作上的有效性。
关键看点
- 统一架构：In-Context RGB-Alpha Token Modeling在单序列联合表征画布与有序RGBA层，实现语义编辑与图层内容显式控制
- 蒸馏策略：Compositional Edit-Prior Distillation将预训练编辑先验迁移至画布及合成图层，适配分层输出并保持编辑保真度
- 数据资产：构建LayerEditor-100K大规模配对数据集，含有序RGBA图层标注及专用分层编辑评测基准，填补训练评估空白
- 应用价值：支持精准局部修改与无关区域保留，生成的可复用RGBA图层可直接服务于具身智能仿真场景构建与资产复用
工程与产业观察
该工作将图像编辑从像素级推向结构化图层级，其生成的RGBA资产可直接用于具身仿真环境搭建与Sim2Real纹理迁移。对于机器人算法工程师而言，这种分层表征能力显著降低了场景泛化数据的制作成本，并为基于视觉语言模型的精细化操作任务提供了更优的中间态表达范式。
英文摘要 (Abstract)
High-quality image editing requires precise modification of target regions while preserving the content of unrelated regions. Existing editing models produce flattened outputs that limit precise local manipulation and layer reuse, while decomposition methods typically optimize layer recovery separately from instruction-driven editing. To this end, we introduce LayerEditor, a unified framework that couples instruction-guided image editing with controllable generation of reusable RGBA layers. At its core, In-Context RGB-Alpha Token Modeling jointly represents the edited canvas and an ordered sequence of RGB-Alpha layers within a single token sequence, enabling semantic edits and explicit control over individual layer content. To retain the pretrained model's editing capability during adaptation to layered outputs, we propose Compositional Edit-Prior Distillation, which transfers its editing prior to both the edited canvas and the image composed from the predicted layers. To support training and evaluation, we construct LayerEditor-100K, a large-scale paired image-editing dataset with ordered RGBA layer annotations, and introduce dedicated benchmarks for layered editing. Extensive experiments demonstrate that LayerEditor maintains strong editing fidelity while generating accurate RGBA layers, supporting both flexible layer-level manipulation and multi-layer decomposition.
Hugging Face Daily Papers 热度：182 upvotes 作者：xue wen, Yong Liu, Xueheng Li, Si Wu, Yong Xu, Yipeng Sun, Yan Li, Simiu Gu
来源
本页事实对应的公开页面，以原文为准。