Ablation Study

[UestcJay]

hi, many thanks for your great work! when I reproduce your result on scan24 of dtu dataset, the eval result is:

mean_d2s, mean_s2d, over_all
0.48679506296355385 0.46026482854092204 0.47352994575223795

but when I use feat loss(comment the bias loss code), the result is:

1.2222348248315786 0.4250271006269524 0.8236309627292655

Where am I going wrong, can you give me some suggestion？

[YZsZY]

Hello, is it convenient to share the preprocessed dataset, the link is not working anymore~

[songsenIng]

Hello, can you share the dtu data set you use? Thank you very much