组编辑：一次编辑多张图像
Group Editing: Edit Multiple Images in One Go
将图像组视为伪视频，利用预训练视频模型的时序一致性先验，并通过 VGGT 提取显式几何对应进行融合，为多图一致编辑提供了可复用的技术路线。
原文依据 we reformulate the image group as a pseudo-video and leverage the temporal coherence priors learned by pre-trained video models
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文研究在一组相关图像上进行一致且统一的修改的问题。该任务尤其具有挑战性，因为这些图像在姿态、视角和空间布局上可能差异显著。实现连贯的编辑需要建立图像间可靠的对应关系，以便修改能够准确地应用于语义对齐的区域。为此，我们提出 GroupEditing，一种新颖的框架，在组内图像之间构建显式和隐式关系。在显式方面，我们使用 VGGT 提取几何对应关系，基于视觉特征提供空间对齐。在隐式方面，我们将图像组重新表述为伪视频，并利用预训练视频模型学到的时序一致性先验来捕获潜在关系。为了有效融合这两种对应关系，我们通过一种新颖的融合机制将来自 VGGT 的显式几何线索注入视频模型。为了支持大规模训练，我们构建了 GroupEditData，这是一个新的数据集，包含大量图像组的高质量掩码和详细描述。此外，为了在编辑过程中确保身份保持，我们引入了一个对齐增强的 RoPE 模块，提高了模型在多个图像间保持外观一致的能力。最后，我们提出了 GroupEditBench，一个专门设计的基准，用于评估组级图像编辑的有效性。大量实验表明，GroupEditing 在视觉质量、跨视角一致性和语义对齐方面显著优于现有方法。
英文原文摘要 1681 字符
In this paper, we tackle the problem of performing consistent and unified modifications across a set of related images. This task is particularly challenging because these images may vary significantly in pose, viewpoint, and spatial layout. Achieving coherent edits requires establishing reliable correspondences across the images, so that modifications can be applied accurately to semantically aligned regions. To address this, we propose GroupEditing, a novel framework that builds both explicit and implicit relationships among images within a group. On the explicit side, we extract geometric correspondences using VGGT, which provides spatial alignment based on visual features. On the implicit side, we reformulate the image group as a pseudo-video and leverage the temporal coherence priors learned by pre-trained video models to capture latent relationships. To effectively fuse these two types of correspondences, we inject the explicit geometric cues from VGGT into the video model through a novel fusion mechanism. To support large-scale training, we construct GroupEditData, a new dataset containing high-quality masks and detailed captions for numerous image groups. Furthermore, to ensure identity preservation during editing, we introduce an alignment-enhanced RoPE module, which improves the model's ability to maintain consistent appearance across multiple images. Finally, we present GroupEditBench, a dedicated benchmark designed to evaluate the effectiveness of group-level image editing. Extensive experiments demonstrate that GroupEditing significantly outperforms existing methods in terms of visual quality, cross-view consistency, and semantic alignment.