phuang17/DeepMVS

Results of trained model

Closed this issue · 2 comments

I've tried on ETH3D dataset with provided trained model, and I got similar but different results, especially with more errors.

I followed the instructions, and conducted sparse reconstruction via colmap.

But the result seems include more errors such as belows.

It's a result of facade in ETH3D benchmark.
image

image

Most of huge errors are in sky region, even though I included MVS-SYNTH dataset in training.

So I've trained the model myself but still I got similar errors and I don't know why.

Is it because of colmap? or am I missing something?

How did you run the sparse reconstruction? Did you run the sparse reconstruction again, or did you use the sparse reconstruction provided from ETH3D's website? I was using the provided one, and I would guess that it led to better results.

Thanks for answering!
I was running the sparse reconstruction again. I got better result with provided one.