新数据集让视频修复更真实，支持从轻微到剧烈运动的精准测试。
MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration
- 用高帧率+专业镜头捕捉复杂运动场景，生成逼真模糊效果。
- 通过光流自适应平均帧，实现一致运动模糊与清晰插帧输入。
- 首个可调控运动幅度的数据集，适合挑战极限的图像修复研究。
我们提出MIORe和VAR-MIORe两个新型多任务数据集，解决当前运动修复基准的关键缺陷。基于1000帧/秒的高帧率采集与专业光学设备，数据集涵盖复杂自车运动、动态多人交互及深度相关的模糊效应。MIORe通过计算光流指标自适应平均帧，生成一致的运动模糊，并保留清晰输入用于视频插帧与光流估计；VAR-MIORe进一步拓展运动幅度范围，从微小到极端，是首个提供显式运动幅值控制的基准。我们提供高分辨率、可扩展的真实值，使现有算法在可控与恶劣条件下均面临挑战，为各类图像与视频修复任务的下一代研究铺平道路。
原文摘要 · Abstract (English)
We introduce MIORe and VAR-MIORe, two novel multi-task datasets that address critical limitations in current motion restoration benchmarks. Designed with high-frame-rate (1000 FPS) acquisition and professional-grade optics, our datasets capture a broad spectrum of motion scenarios, which include complex ego-camera movements, dynamic multi-subject interactions, and depth-dependent blur effects. By adaptively averaging frames based on computed optical flow metrics, MIORe generates consistent motion blur, and preserves sharp inputs for video frame interpolation and optical flow estimation. VAR-MIORe further extends by spanning a variable range of motion magnitudes, from minimal to extreme, establishing the first benchmark to offer explicit control over motion amplitude. We provide high-resolution, scalable ground truths that challenge existing algorithms under both controlled and adverse conditions, paving the way for next-generation research of various image and video restoration tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。