dtu数据集 - Githubissues

ewrfcas / MVSFormer

Codes of MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth (TMLR2023)

Apache License 2.0

175 stars 10 forks source link

Closed ligang305 closed 1 year ago

ligang305 commented 1 year ago

您好，请问为什么选择用原尺寸（DTU_origin/Rectified）图片呢？（而不用预处理过的图片）我想在UniMVSNet上用一下Twins来处理FPN提取到的特征，该咋弄呢。谢谢大佬

ewrfcas commented 1 year ago

More information could be found in our paper (Section3.2 Efficient Multi-scale Training).