Whether to use the foreground mask when calculating the F1-score of Tanks and Temples in Table 2 in the paper?

[zhuixunforever]

Hi, thanks for the wonderful work. Whether you use the foreground mask when calculating the F1-score of TaT, just like using the IDR mask when calculating the chamfer distance of DTU. Or directly use the output 3D surface (the reconstruction range may be larger than ground truth) to calculate F1-score?