RecEdit-Drive：面向自动驾驶场景的3D重建引导时空视频编辑
RecEdit-Drive: 3D Reconstruction-Guided Spatiotemporal Video Editing for Autonomous Driving Scenes
利用3D重建得到的背景结构作为扩散去噪早期的参考，并通过空间特征变形约束动态前景物体的编辑，为视频编辑中保持动态3D对象时空一致性提供了可复用的思路。
原文依据 we design an inference strategy to reconstruct an accurate background structure through noise manipulation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在电影制作和自动驾驶等领域，高质量的视频编辑与处理至关重要，因为精确的视觉精修和数据准备不可或缺。然而，在保持时空一致性的同时实现对动态对象的精确控制颇具挑战。现有方法通常利用文本提示或2D结构先验进行视频编辑以保证一致性，但难以有效约束动态3D对象在空间上的变化。本文提出RecEdit-Drive，一个融合空间特征变形与时空协同建模的框架，可有效控制3D对象的变化并增强视频一致性。空间特征变形增强了对被编辑前景3D对象的精确控制，提升了生成视频的空间一致性；时空协同建模则将编辑后的前景对象无缝融入背景，生成真实且一致的编辑视频。此外，我们设计了一种推理策略，通过噪声操纵重建准确的背景结构，在去噪早期为前景实例编辑提供可靠参考。我们在公开数据集上针对通用视频编辑与下游任务进行了大量定性与定量比较，证明了所提方法达到最优性能。
英文原文摘要 1441 字符
High-quality video editing and processing are crucial in domains such as filmmaking and autonomous driving, where accurate visual refinement and data preparation are essential. However, it is challenging to achieve precise control over dynamic objects while maintaining spatiotemporal consistency. Current approaches typically utilize text prompts or 2D structural priors for video editing to ensure consistency, yet they struggle to effectively constrain the spatial variations of dynamic 3D objects. In this paper, we introduce RecEdit-Drive, a framework that integrates Spatial Feature Warping and Spatiotemporal Collaborative Modeling to effectively control 3D object variations and enhance video consistency. The spatial feature warping enhances precise control over the edited foreground 3D objects, enhancing spatial consistency in the generated videos; and the spatiotemporal collaborative modeling seamlessly integrates edited foreground objects into the background, yielding realistic and consistent edited videos. Besides, we design an inference strategy to reconstruct an accurate background structure through noise manipulation, providing a reliable reference for foreground instance editing at early denoising stages. We perform extensive qualitative and quantitative comparisons regarding general video editing and downstream tasks on the public datasets, demonstrating the state-of-the-art performance of our proposed method.