search

JeffWang987 / MVSTER

[ECCV 2022] MVSTER: Epipolar Transformer for Efficient Multi-View Stereo
MIT License
183 stars 13 forks source link

The output .ply. Could you explain what are they ? #8

Open GabbySuwichaya opened 1 year ago

GabbySuwichaya commented 1 year ago

Thank you for sharing the repo! and for producing this awesome ECCV paper !!!

It is my first time working on this topic, so I would like to kindly ask questions about the output files.

Here, I have seen two sets of outputs. One set of the .ply files is in scanX/ply_local folders, where of each of scanX contains the following output folders, cam, confidence, depth_est, images, mask, and ply_local. The other set of .ply files is those mvsnetXXX_l3.ply

So, my questions are

  1. Which one is the output from MVSTER? What is the meaning of each of these .ply files? For example, why there are two sets of them? (Please see the figure below for the examples)

  2. Is mvsnetXXX_l3.ply used for comparison? or it is also output from MVSTER?

  3. In each of scanX/ply_local folder, there are 3 .ply files... What are they? What is the meaning for each of them? (Please see the figure below for the examples)

  4. How did you visualize them..?. I am so sorry for asking this question. I only would like to learn from you. I have used Open3d, but it looks like the following which does not look as good as the example. I only use the command open3d draw

Question 1 & 2 Question 3 Question 4 Question 4
Screenshot from 2022-09-22 14-16-56 Screenshot from 2022-09-22 14-17-12 Screenshot from 2022-09-22 14-36-07 Screenshot from 2022-09-22 14-32-03 Screenshot from 2022-09-22 14-32-15
JeffWang987 commented 1 year ago
  1. "mvsnet_xxx_l3.ply" is the final point cloud output of the scan xxx, and other ply files (e.g., scan1/ply_local/00000000.ply) are the intermediate point clouds for simple visualization. To be more specific, to produce 00000000.ply, we run the model for 00000000.png (along with its source images) and generate the depth map for 00000000.png. Then we can convert the depth map to point cloud file 00000000.ply with the camera parameters. In contrast, to produce mvsnet_xxx_l3.ply, we have to run the model for every single frame (000000.png-xxxxxx.png), and generate depth maps for each of them, subsequently, these depth maps are fused to calculate the mvsnet_xxx_l3.ply.
  2. mvsnetXXX_l3.ply is used to evaluate the DTU dataset for model comparison.
  3. see 1
  4. You can use Open3d to visualize these point clouds. For better visualization, you may want to visualize the whole point cloud of the scan (mvsnetXXX_l3.ply ), instead of the point cloud from a single depth map (0000000.ply).