EVENTAID
收藏资源简介:
EVENTAID数据集是由北京大学计算机学院的研究团队创建,专注于事件辅助的图像和视频增强技术。该数据集包含19种不同的算法,用于评估五种主要的事件辅助图像/视频增强任务,包括基于事件的视频重建、事件辅助的高帧率视频重建、图像去模糊、图像超分辨率和高动态范围图像重建。数据集通过精确的时空同步技术,使用“Event-RGB”混合多摄像机系统收集,确保了场景的多样性,旨在解决传统帧摄像机在曝光时间、分辨率、动态范围和帧率方面的限制。
EVENTAID dataset was developed by a research team from the School of Computer Science, Peking University, focusing on event-aided image and video enhancement technologies. This dataset encompasses 19 distinct algorithms for evaluating five core event-aided image and video enhancement tasks, including event-based video reconstruction, event-aided high-frame-rate video reconstruction, image deblurring, image super-resolution, and high dynamic range (HDR) image reconstruction. The dataset was collected using an "Event-RGB" hybrid multi-camera system with precise spatiotemporal synchronization technology, which ensures the diversity of the captured scenarios, and aims to address the limitations of traditional frame cameras in terms of exposure time, resolution, dynamic range and frame rate.

- 1EventAid: Benchmarking Event-aided Image/Video Enhancement Algorithms with Real-captured Hybrid Dataset北京大学计算机学院 · 2023年



