search

Parskatt / DKM

[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation
https://parskatt.github.io/DKM/
Other
378 stars 28 forks source link

scannet test code #54

Closed jdk9405 closed 5 months ago

jdk9405 commented 5 months ago

Hi,

Thank you for sharing your work. It's been helpful for my research. However, I'm quite new to the dense matching method and have some simple questions regarding the scannet data test code.

I noticed that the error computing process is iterated five times. Is it a normal metric in other dense matching tasks like loftr or PDC-Net+? https://github.com/Parskatt/DKM/blob/main/dkm/benchmarks/scannet_benchmark.py#L98

for _ in range(5):
    shuffling = np.random.permutation(np.arange(len(kpts1)))
    ...

Additionally, I saw another line that adds errors after the loop. This might include the same error twice. https://github.com/Parskatt/DKM/blob/main/dkm/benchmarks/scannet_benchmark.py#L120

for _ in range(5):
    ...  
    tot_e_t.append(e_t)
    tot_e_R.append(e_R)
    tot_e_pose.append(e_pose)
tot_e_t.append(e_t)
tot_e_R.append(e_R)
tot_e_pose.append(e_pose)

Thanks in advance.

Parskatt commented 5 months ago

Hi! The first thing is to reduce the variance, the second thing is a bug (although not a severe one), good find!

Could you submit a pr to just remove that unneeded line?