首个融合图像与事件数据的多任务对应关系基准，支持光流、场景流和点跟踪评估。
BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events
- 构建包含图像与事件数据的多模态数据集，支持密集标注。
- 涵盖410类日常物体，覆盖真实场景中的运动与形变等复杂因素。
- 适合研究事件视觉、三维运动估计及多模态感知的学者使用。
事件视觉系统能以无帧率限制和高动态范围持续观测场景，适用于光流与点跟踪等对应关系任务。然而，现有基准缺乏同时包含事件数据与图像的综合性评测体系。为此，我们提出BlinkVision，一个大规模、多样化的多模态基准，提供光学流、场景流和点跟踪的密集像素级标注。该数据集包含410种日常物体类别，与LVIS和ShapeNet等主流2D/3D数据集共享类别；具备逼真的视觉效果，涵盖相机抖动、形变等自然因素。BlinkVision支持基于图像与事件的光流、点跟踪和场景流估计算法的全面评测，为未来研究提供新发现与实践参考。官网：https://www.blinkvision.net/
原文摘要 · Abstract (English)
Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynamic range, making them well-suited for correspondence tasks such as optical flow and point tracking. However, there is still a lack of comprehensive benchmarks for correspondence tasks that include both event data and images. To address this gap, we propose BlinkVision, a large-scale and diverse benchmark with multiple modalities and dense correspondence annotations. BlinkVision offers several valuable features: 1) Rich modalities: It includes both event data and RGB images. 2) Extensive annotations: It provides dense per-pixel annotations covering optical flow, scene flow, and point tracking. 3) Large vocabulary: It contains 410 everyday categories, sharing common classes with popular 2D and 3D datasets like LVIS and ShapeNet. 4) Naturalistic: It delivers photorealistic data and covers various naturalistic factors, such as camera shake and deformation. BlinkVision enables extensive benchmarks on three types of correspondence tasks (optical flow, point tracking, and scene flow estimation) for both image-based and event-based methods, offering new observations, practices, and insights for future research. The benchmark website is https://www.blinkvision.net/.
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。