RainVID&SS

Citation Author(s):
Shangquan
Sun
Submitted by:
Shangquan Sun
Last updated:
Tue, 07/26/2022 - 02:49
DOI:
10.21227/ys89-k082
License:
35 Views
Categories:
0
0 ratings - Please login to submit your rating.

Abstract 

We create a RainVID&SS benchmark on which the performance gain of subsequent processes with and without deraining pre-process can be evaluated. We argue that the gain can be a metric of deraining methods from a computer perspective

Instructions: 

We propose a dataset RainVID&SS , whose rain-free videos are selected from a common dataset in video object detection, ImageNet-VID and a dataset in video semantic segmentation, CamVid. For each video, rain streaks are rendered by After Effects with the opacity of 1. ImageNet-VID + means the subset of videos from ImageNet-VID and CamVid + means the subset from CamVid

Dataset Files

    Files have not been uploaded for this dataset