OpenVE-3M: 一种大规模高质量的指令引导视频编辑数据集
OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing
AI总结：
OpenVE-3M是一个大规模高质量的指令引导视频编辑数据集，包含多种编辑类型，通过精心设计的数据管道生成，并展示了高效的5B模型在基准测试中的卓越性能。
摘要：
基于指令的图像编辑数据集的质量和多样性持续增加，然而针对基于指令的视频编辑的大规模、高质量数据集仍然稀缺。为解决这一差距，我们引入了OpenVE-3M，这是一个开源、大规模且高质量的数据集，用于基于指令的视频编辑。它包含两个主要类别：空间对齐的编辑（全局风格、背景改变、局部改变、局部移除、局部添加和字幕编辑）和非空间对齐的编辑（摄像机多镜头编辑和创意编辑）。所有编辑类型均通过精心设计的数据管道生成，并经过严格的质量筛选。OpenVE-3M在规模、编辑类型多样性、指令长度和整体质量方面均优于现有开源数据集。此外，为解决该领域缺乏统一基准的问题，我们构建了OpenVE-Bench，包含431个视频编辑对，涵盖了多样化的编辑任务，其三个关键指标高度符合人类判断。我们提出了OpenVE-Edit，一个在我们数据集上训练的5B模型，通过在OpenVE-Bench上设置新的最先进的性能，显著优于所有先前的开源模型，包括一个14B的基线模型。项目页面位于https://lewandofskee.github.io/projects/OpenVE。
英文摘要：
The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain scarce. To address this gap, we introduce OpenVE-3M, an open-source, large-scale, and high-quality dataset for instruction-based video editing. It comprises two primary categories: spatially-aligned edits (Global Style, Background Change, Local Change, Local Remove, Local Add, and Subtitles Edit) and non-spatially-aligned edits (Camera Multi-Shot Edit and Creative Edit). All edit types are generated via a meticulously designed data pipeline with rigorous quality filtering. OpenVE-3M surpasses existing open-source datasets in terms of scale, diversity of edit types, instruction length, and overall quality. Furthermore, to address the lack of a unified benchmark in the field, we construct OpenVE-Bench, containing 431 video-edit pairs that cover a diverse range of editing tasks with three key metrics highly aligned with human judgment. We present OpenVE-Edit, a 5B model trained on our dataset that demonstrates remarkable efficiency and effectiveness by setting a new state-of-the-art on OpenVE-Bench, outperforming all prior open-source models including a 14B baseline. Project page is at https://lewandofskee.github.io/projects/OpenVE.
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。
