jzhangbs / MVSDF

Learning Signed Distance Field for Multi-view Surface Reconstruction
MIT License
136 stars 9 forks source link

question about evaluation on EPFL dataset #3

Closed gaobodaxinwen closed 2 years ago

gaobodaxinwen commented 2 years ago

Thanks for sharing this great work. I am curious about the evaluation on EPFL fountain and Herzjesu dataset. It seems that you use this script to evaluate on the DTU dataset. Do you use the same script to evaluate on EPFL dataset ? What's more, could you please provide the masks of images and gt point clouds of EPFL dataset?

jzhangbs commented 2 years ago

Thanks for your interest in our work! Related data can be downloaded from iccv21_assets.zip

chamfer.py - evaluation code for chamfer distance, there is brief instruction for the usage *.ply - processed ground truth (fountain|herzjesu)_(main|full) - manually labeled masks

For PSNR evaluation, we also take the intersection of the rendering masks across all the methods.

gaobodaxinwen commented 2 years ago

Thanks for your quick and detailed reply!