用于一致3D场景编辑的基于扩散的注意力扭曲方法
Diffusion-Based Attention Warping for Consistent 3D Scene Editing
AI总结：
本研究提出一种基于扩散模型的3D场景编辑方法，通过单参考图注意力特征结合高斯溅射深度几何对齐实现多视角特征扭曲，保障编辑的视图一致性与真实感，显著提升3D场景编辑能力。
摘要：
我们提出了一种利用扩散模型进行3D场景编辑的新方法，旨在确保跨视角的视图一致性与真实感。该方法利用从单张参考图像中提取的注意力特征来定义预期编辑内容，通过将这些特征与基于Gaussian splatting（高斯溅射）深度估计得到的场景几何对齐，实现多视角间的特征扭曲。将扭曲后的特征注入其他视角，可实现编辑内容的连贯传播，在3D空间中达到高保真度与空间对齐效果。大量评估证明了该方法在生成多样化3D场景编辑方面的有效性，与现有方法相比显著提升了场景操作能力。项目页面：https://attention-warp.github.io
英文摘要：
We present a novel method for 3D scene editing using diffusion models, designed to ensure view consistency and realism across perspectives. Our approach leverages attention features extracted from a single reference image to define the intended edits. These features are warped across multiple views by aligning them with scene geometry derived from Gaussian splatting depth estimates. Injecting these warped features into other viewpoints enables coherent propagation of edits, achieving high fidelity and spatial alignment in 3D space. Extensive evaluations demonstrate the effectiveness of our method in generating versatile edits of 3D scenes, significantly advancing the capabilities of scene manipulation compared to the existing methods. Project page: \url{https://attention-warp.github.io}
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。
