hzxie / Pix2Vox

The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (Xie et al., ICCV 2019)

Home Page:https://haozhexie.com/project/pix2vox

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

What is the meaning of "Baseline" in the test results?

sujuyu opened this issue · comments

I'm sorry to trouble you again. I want to know the meaning of this dataline in the test process. A little help from you would be greatly appreciated
image
Thank you very much.

"Baseline" is the IoU of 3D-R2N2. Because we take 3D-R2N2 as our baseline.

Hello, I want to ask what does t=0.20 t=0.30 t=0.40 t=0.50 mean.Thank you very much.

Hello, I want to ask what does t=0.20 t=0.30 t=0.40 t=0.50 mean.Thank you very much.

It means the voxelization threshold. For example, if a floating-point number in the output matrix is 0.35 (representing the voxel probability), this position is not occupied at t = 0.4, but is occupied if t = 0.3 is selected. The final result only has 0 indicating unused and 1 indicating occupied, but the output matrix is a floating point number representing probability, so t is required to do binarization processing. Generally, t = 0.3 or t = 0.4 is the best choice

I get it, thanks a lot for your reply.