使用雨水去除技術可以幫助許多戶外視覺應用，使得雨水影像變清晰。在本文中，我們提供了一種自動從雨水影像中找出雨水模板的方法，並利用這些模板更新雨水字典，使雨水字典能學習該張影像的雨水特性。我們也說明如何判別一個區塊是否為雨水區塊的可能性，並依據判別結果修改縮減係數。實驗結果顯示，與現有的方法相比，我們的方法顯示出更好的結果 Using rain removal technique to make a raining image clean can help in many outdoor visual applications. In this paper we present an automatic way to choose rain templates from a given raining image. With these templates, rain dictionary is modified. We also illustrate how to determine the likelihood of a patch being a raining patch. Shrinkage coefficient is modified according to such likelihood. Our method is shown to have better results comparing to existing similar methods.
