Ground truth ply for Tanks and Temple intermediate test set

[320160040]

The official T&T dataset provides code for calculating F-Score along with ground truth plys for Training sets. The evaluation code requires ground truth data to compare with predicted data. However, I could not find ground truth data for intermediate test sets anywhere. So I wanted to ask if you created that by yourself by using some third-party software like COLMAP?

[tourlics]

The official T&T dataset provides code for calculating F-Score along with ground truth plys for Training sets. The evaluation code requires ground truth data to compare with predicted data. However, I could not find ground truth data for intermediate test sets anywhere. So I wanted to ask if you created that by yourself by using some third-party software like COLMAP?

Hello, it seems that the groundtruth of official T&T Testing dataset is not public, we can only submit our model to the online benchmark to get the F-score (like the table in this picture).

[wangchengze001]

how to change in code test.py，i can eval the T&T dataset

[zhao-you-fei]

@320160040 @wangchengze001 @tourlics @gxd1994 @alibaba-oss 请教一下我在casmvsnet上测试T&T数据集没有报错,filter-method用的normal,为什么我的点云融合不成功或者说效果很差,ply_local文件夹下中间点云效果也不好,深度图效果也很差(如下图) 最后结果: ply_local文件夹下中间点云: 深度图: