RNA：基于ROI的神经图谱视频编辑
RNA: Video Editing with ROI-based Neural Atlas
AI总结：
提出基于ROI的神经图谱（RNA）视频编辑框架，通过用户指定编辑区域省去前景分离与建模，并设计掩码细化方法和软神经图谱模型解决遮挡与重建问题，实现更高效高质量的视频编辑。
摘要：
随着基于视频的社交网络服务（SNS）平台的近期增长，普通用户对视频编辑的需求不断增加。然而，由于相机移动和运动物体等随时间变化的因素，视频编辑可能具有挑战性。虽然现代基于图谱的视频编辑方法已经解决了这些问题，但它们通常无法编辑包含复杂运动或多个运动物体的视频，并且即使对于非常简单的编辑也需要过高的计算成本。在本文中，我们提出了一种新颖的基于感兴趣区域（ROI）的视频编辑框架：基于ROI的神经图谱（RNA）。与先前的工作不同，RNA允许用户指定编辑区域，通过消除对前景物体进行前景分离和图谱建模的需求来简化编辑过程。然而，这种简化带来了一个独特的挑战：在不依赖额外分割模型的情况下，获取能够有效处理由运动物体引起的编辑区域中遮挡的掩码。为了解决这个问题，我们提出了一种针对这一特定挑战设计的新颖掩码细化方法。此外，我们引入了一种用于视频重建的软神经图谱模型，以确保高质量的编辑结果。大量实验表明，与先前的方法相比，RNA提供了一种更实用、更高效的编辑解决方案，适用于更广泛的视频且具有更高质量。
英文摘要：
With the recent growth of video-based Social Network Service (SNS) platforms, the demand for video editing among common users has increased. However, video editing can be challenging due to the temporally-varying factors such as camera movement and moving objects. While modern atlas-based video editing methods have addressed these issues, they often fail to edit videos including complex motion or multiple moving objects, and demand excessive computational cost, even for very simple edits. In this paper, we propose a novel region-of-interest (ROI)-based video editing framework: ROI-based Neural Atlas (RNA). Unlike prior work, RNA allows users to specify editing regions, simplifying the editing process by removing the need for foreground separation and atlas modeling for foreground objects. However, this simplification presents a unique challenge: acquiring a mask that effectively handles occlusions in the edited area caused by moving objects, without relying on an additional segmentation model. To tackle this, we propose a novel mask refinement approach designed for this specific challenge. Moreover, we introduce a soft neural atlas model for video reconstruction to ensure high-quality editing results. Extensive experiments show that RNA offers a more practical and efficient editing solution, applicable to a wider range of videos with superior quality compared to prior methods.
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。
