自由形式场景编辑器：实现类似3D引擎中的多轮物体操控
Free-Form Scene Editor: Enabling Multi-Round Object Manipulation like in a 3D Engine
AI总结：
针对现有文本到图像扩散模型难以完成3D感知物体操控的问题，提出自回归框架FFSE与配套数据集3DObjectEditor，可实现多轮物理一致的真实图像3D物体编辑，性能优于现有方法。
摘要：
近期文本到图像（T2I）扩散模型的进展大幅提升了语义图像编辑能力，但多数方法无法完成具备3D感知的物体操控。本研究提出FFSE（自由形式场景编辑器），这是一个具备3D感知的自回归框架，旨在直接在真实图像上实现直观、物理一致的物体编辑。不同于此前要么在图像空间操作、要么需要缓慢且易出错的3D重建的方法，FFSE将编辑建模为一系列习得的3D变换，支持用户执行平移、缩放、旋转等任意操控，同时保留阴影、反射等真实背景效果，并在多轮编辑中维持全局场景一致性。为支撑多轮3D感知物体操控的学习，我们构建了混合数据集3DObjectEditor，该数据集由跨多样物体与场景的模拟编辑序列构成，可支持多轮动态条件下的有效训练。大量实验表明，所提出的FFSE在单轮和多轮3D感知编辑场景中均显著优于现有方法。
英文摘要：
Recent advances in text-to-image (T2I) diffusion models have significantly improved semantic image editing, yet most methods fall short in performing 3D-aware object manipulation. In this work, we present FFSE, a 3D-aware autoregressive framework designed to enable intuitive, physically-consistent object editing directly on real-world images. Unlike previous approaches that either operate in image space or require slow and error-prone 3D reconstruction, FFSE models editing as a sequence of learned 3D transformations, allowing users to perform arbitrary manipulations, such as translation, scaling, and rotation, while preserving realistic background effects (e.g., shadows, reflections) and maintaining global scene consistency across multiple editing rounds. To support learning of multi-round 3D-aware object manipulation, we introduce 3DObjectEditor, a hybrid dataset constructed from simulated editing sequences across diverse objects and scenes, enabling effective training under multi-round and dynamic conditions. Extensive experiments show that the proposed FFSE significantly outperforms existing methods in both single-round and multi-round 3D-aware editing scenarios.
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。
