SpatialDiff：通过隐式空间建模实现三维感知的物体移动
SpatialDiff: 3D-Aware Object Movement via Implicit Spatial Modeling
把隐式三维空间先验注入扩散编辑模型，并用全局空间监督约束潜变量，为在复杂遮挡与跨深度场景下做一致的对象移动提供可复用思路。
原文依据 Implicit 3D Spatial Modeling, which introduces 3D prior knowledge and enables the model to internally build a comprehensive understanding
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期图像编辑的进展实现了令人印象深刻的物体操控，但现有方法仍难以处理复杂场景中的空间移动，例如物体跨越不同深度层或被部分遮挡的情形。多数图像编辑方法仅关注来自二维数据集的先验信息，强调平面特征而缺乏对空间结构的支持。即便是引入显式位置信息的方法，也无法捕捉真实的三维空间关系，从而限制了复杂场景中准确的物体移动。本文提出 SpatialDiff，一种能够有效捕捉三维空间结构的方法，可在复杂场景中实现精确且一致的物体移动。我们的核心创新有两点：（1）隐式三维空间建模，引入三维先验知识，使模型在内部建立起对三维空间结构的全面理解；（2）全局空间监督，对潜变量空间特征施加约束，使模型能够感知编辑操作所引起的物体空间位置变化。实验结果表明，我们的方法显著提升了复杂场景中空间移动的准确性与保真度。
英文原文摘要 1247 字符
Recent advances in image editing allow impressive manipulation of objects, existing methods still struggle to handle spatial movement in complex scenes, such as objects span different depth layers or are partially occluded. Most image editing methods focus solely on prior information from 2D datasets, emphasizing planar features while lacking support for spatial structures. Even approaches that incorporate explicit positional information fail to capture true 3D spatial relationships, thus limiting accurate object movement in complex scenes. In this paper, we present SpatialDiff, a method that effectively captures 3D spatial structures, enabling precise and consistent object movements in complex scenes. Our core innovations are twofold: (1) Implicit 3D Spatial Modeling, which introduces 3D prior knowledge and enables the model to internally build a comprehensive understanding of the three-dimensional spatial structure; and (2) Global Spatial Supervision, which constrains the latent spatial features to enable the model to perceive changes in object spatial positions caused by editing operations. Experimental results demonstrate that our method significantly improves the accuracy and fidelity of spatial movement in complex scenes.