search

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

[ICCV2021]"DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network", https://arxiv.org/abs/2207.10434
212 stars 21 forks source link

I am confused about the quantitative results in table1(RMSE on SRD). #5

Closed nachifur closed 2 years ago

nachifur commented 2 years ago

Your work is novel. Thank you for your great work! I am confused by the quantitative results in Table 1, they seem to be much better than the results in the original paper. How are these results obtained? image I am very much looking forward to your reply. Thanks again for your work.

jinyeying commented 2 years ago

Your work is novel. Thank you for your great work! I am confused by the quantitative results in Table 1, they seem to be much better than the results in the original paper. How are these results obtained? image I am very much looking forward to your reply. Thanks again for your work.

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).

jinyeying commented 2 years ago

Your work is novel. Thank you for your great work! I am confused by the quantitative results in Table 1, they seem to be much better than the results in the original paper. How are these results obtained? image I am very much looking forward to your reply. Thanks again for your work.

In their original papers, the image resolution they use is the original image size. Since I used RTX 2080 Ti to train the model with 256x256 image resolution, all the baseline results are resized to 256x256 for a fair comparison.