jinyeying/DC-ShadowNet-Hard-and-Soft-Shadow-Removal

evaluation

Halfpoint1 opened this issue · 7 comments

Halfpoint1 commented

Sorry to interrupt you, I want to ask you some questions. Is the RMSE index of the input image of the ISTD+ dataset in your paper measured with your matlab code? I tested different results, and I am confused about the evaluation indicators. I hope you can help me answer my doubts, thank you.

jinyeying commented

Sorry to interrupt you, I want to ask you some questions. Is the RMSE index of the input image of the ISTD+ dataset in your paper measured with your matlab code? I tested different results, and I am confused about the evaluation indicators. I hope you can help me answer my doubts, thank you.

Yes, I double-checked, the number is correct.

SRD Dataset set the paths of the shadow removal result and the dataset in demo_srd_release.m and then run it.
Get the following Table 1 in the main paper on the SRD (size: 256x256).

Halfpoint1 commented
Halfpoint1 commented
jinyeying commented

I tried it again. I found that your method is the same as the paper, but got different results for the Input Image of AISTD.
…
------------------ 原始邮件 ------------------ 发件人: "jinyeying/DC-ShadowNet-Hard-and-Soft-Shadow-Removal" @.>; 发送时间: 2022年1月6日(星期四) 中午11:00 @.>; @.@.>; 主题: Re: [jinyeying/DC-ShadowNet-Hard-and-Soft-Shadow-Removal] evaluation (Issue #4) For AISTD, the number is the same as the paper. https://www.dropbox.com/sh/foqmi8olum6n3qz/AADX3aQ4yzWvKHh4wtAF6YREa?dl=0 — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you authored the thread.Message ID: @.***>

For the input, we get the number from the paper “from shadow segmentation to shadow removal”. You can find their paper as a reference. Our evaluation code is the same as theirs.

Halfpoint1 commented
jinyeying commented

Welcome, and I may close the question.