Thans for your great job! And I have two questions：
(1) Is there a difference between the multi-view depth estimation task (your work) and the multi-view stereo (MVS) task? I'm confused that why MVSNet and the methods derived from it are not compared in your experiment.
(2) Why did you only conduct the experiment on the dataset ScanNet?
Looking forward to your reply.
Thank you very much.
Thans for your great job! And I have two questions：
(1) Is there a difference between the multi-view depth estimation task (your work) and the multi-view stereo (MVS) task? I'm confused that why MVSNet and the methods derived from it are not compared in your experiment.
(2) Why did you only conduct the experiment on the dataset ScanNet?
Looking forward to your reply.
Thank you very much.