IMAGHarmony：具有一致物体数量和布局的可控图像编辑
IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layout
AI总结：
本文提出IMAGHarmony，通过和谐感知模块和偏好引导噪声选择策略，在保持物体数量和布局一致性的前提下实现多物体场景的可控图像编辑，实验表明其在结构一致性和语义准确性上优于现有方法。
摘要：
尽管扩散基图像编辑技术取得了进展，但操控多物体场景仍具挑战性。现有方法往往在语义改变上牺牲结构一致性，无法在不引入意外重定位或背景修改的情况下保持精确的物体数量和空间布局。为解决这一限制，我们引入了数量和布局一致的图像编辑（QL-Edit）方法，以修改物体语义的同时保持原始实例数量和空间布局。我们提出IMAGHarmony，一个参数高效框架，包含和谐感知（HA）模块，将参考图像的感知线索融入扩散过程。这使模型能够联合推理物体语义、数量和空间位置，以提高结构一致性。此外，我们引入了偏好引导噪声选择（PNS）策略，以识别有利的初始化条件，显著提高了在挑战性多物体场景中的生成稳定性。为了支持系统评估，我们构建了HarmonyBench基准，旨在测量在数量和布局约束下的语义编辑准确性和结构一致性。广泛实验表明，IMAGHarmony在结构保持和语义准确性方面均优于现有方法。值得注意的是，我们的框架非常高效，仅需200张训练图像和10.6M可训练参数。代码、模型和数据可在\url{https://github.com/muzishen/IMAGHarmony}获取。
英文摘要：
Despite advances in diffusion-based image editing, manipulating multi-object scenes remains challenging. Existing approaches often achieve semantic changes at the expense of structural consistency, failing to preserve exact object counts and spatial layouts without introducing unintended relocations or background modifications. To address this limitation, we introduce quantity-and-layout-consistent image editing (QL-Edit) to modify object semantics while maintaining the original instance cardinality and spatial layout. We propose IMAGHarmony, a parameter-efficient framework featuring a harmony-aware (HA) module that incorporates perception cues from the reference image into the diffusion process. This enables the model to jointly reason about object semantics, counts, and spatial positions for improved structural consistency. Furthermore, we introduce a preference-guided noise selection (PNS) strategy that identifies favorable initialization conditions, substantially improving generation stability in challenging multi-object scenarios. To support systematic evaluation, we construct HarmonyBench, a benchmark designed to measure semantic editing accuracy and structural consistency under quantity and layout constraints. Extensive experiments demonstrate that IMAGHarmony consistently outperforms existing methods in both structural preservation and semantic accuracy. Notably, our framework is highly efficient, requiring only 200 training images and 10.6M trainable parameters. Code, models, and data are available at \url{https://github.com/muzishen/IMAGHarmony}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
