RNA: Video Editing with ROI-based Neural Atlas

TL;DR

RNA introduces a user-friendly ROI-based neural atlas framework for efficient and high-quality video editing, effectively handling complex motions and occlusions without requiring foreground segmentation.

Contribution

The paper presents a novel ROI-based neural atlas method that simplifies video editing by allowing region specification and introduces a mask refinement technique for occlusion handling.

Findings

Outperforms prior methods in editing quality

Handles complex motion and occlusions effectively

Offers practical and efficient video editing solution

Abstract

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.