Test on Tanks and Temples
caoPhoenix opened this issue · 5 comments
Hi, thanks for your excellent works.
I run the code of origin CasMVSNet, and test on Tanks and Temples with their pretrained model.
Then I found that if I don't adjust the number of planes(which is "48,32,8"), the result point cloud looks bad. And after I adjusting the number of the plane of the coarsest level to 160(or 192), the result point cloud is much better.
And I noticed that in your eval.py code, the number of planes is still "48,32,8", and your release had mentioned that Fusion results for all scans using default parameters. What's more, the point cloud you provide focus on a smaller scene range, while it contains much more points than what I got in origin CasMVSNet(after I adjust the number of the plane of the coarsest level).
I wonder how you achieve the wonderful result. Thank you very much!
What's more, I notice that the strategy which you set the depth_interval of scan in Tanks and Temples seems doesn't fit the relationship of n_depths(48×4=192) and interval (according to your comment). Could this be the reason?
Well, I guess I realize the reason. You ignore the DEPTH_NUM and DEPTH_MAX in camera files, and set a smaller depth_interval then the value in camera files. Follow your strategy, I try again on origin CasMVSNet and got a better point cloud although the number of points is only half of yours (Anyway, it looks better).
@caoPhoenix 您好，不知道您是怎么解决这个问题的，我在colmap2mvsnet 相机转化参数 设置的depth_interval = 2 产生的深度图完全是错误的
@caoPhoenix ，您好，我想请教您如何完成CasMVSNet在tank数据集重建点云，感谢您的回复，我被这个问题困扰一周了。