AI 中文总结
本研究提出调度补全方法，实现交互式生成运动编辑，结合运动合成与编辑，可优化现有动画并支持多类编辑应用，经多组实验验证有效。
AI 中文摘要
运动编辑是视觉特效（VFX）与游戏开发的核心环节，被广泛用于修改和增强现有动作，使其适配新环境或艺术方向的调整。传统运动编辑仅能完成小幅修改，无法应对更大规模的结构编辑，会产生视觉扭曲伪影，需要重新创作动作。相反，近期大规模生成建模的进展解锁了通过直接操控稀疏空间约束创作完整动作的新能力，这类方法虽能生成新动作，却缺乏交互式保留和编辑现有动作的能力。本研究提出调度补全（scheduled inpainting），这一方法可实现交互式生成运动编辑，是一种结合运动合成与编辑的新范式，依托生成模型实现。调度补全是一种简单却强大的基于推理的技术，能对保留原始动作与生成新内容的平衡实现细粒度时空控制。我们的系统构建于支持直接操控的生成模型之上，允许创作者交互式优化现有动画，同时确保结果自然且符合学习到的动作分布。调度补全具有通用性，支持扩展、拼接、合成不同片段等多种编辑应用。最后，我们通过与四个基线方法对比、对设计进行 ablation 实验并报告用户反馈，对所提方法进行了全面验证。
英文摘要
Motion editing is central to VFX and game development, where it is used extensively to modify and augment existing movements to conform to new environments or changes in artistic direction. While traditional motion editing can do small modifications, it cannot accommodate larger structural edits, resulting in visual warping artifacts that require authoring new motion. Conversely, recent advances in large-scale generative modeling have unlocked newfound capabilities for authoring entire movements by directly manipulating sparse spatial constraints. While impressive at creating new movements, these methods lack the capability to preserve and edit existing motion interactively. In this work, we introduce scheduled inpainting, a method that enables interactive generative motion editing, a novel paradigm unifying motion synthesis and editing by leveraging generative models. Scheduled inpainting is a simple yet powerful inference-based technique that enables fine-grained spatiotemporal control over the balance between preserving the original motion and generating new content. By building atop generative models that support direct manipulation, our system allows artists to interactively refine existing animations while ensuring results remain natural and consistent with the learned motion distribution. Scheduled inpainting is versatile and supports many editing applications, such as extending, stitching, and compositing different clips. Finally, we extensively validate our approach by comparing with four baselines, conducting ablations of our design, and reporting user feedback.
