Not good performance in an open source dataset

Question

Not good performance in an open source dataset

city19992 opened this issue a year ago · 5 comments

city19992 commented a year ago

Nice job. I tested your code on an open source which could be download from https://doc.arcgis.com/en/drone2map/latest/help/sample-data.htm.

But the reconstructed geometry is not so reasonable. Is there any possible reason?

The first one was trained based on neuralangelo-colmap_sparse-50k.yaml. In the second experiment, I centered and scaled the 3D point cloud into NDC space and set the sampling range of ray marching to the outer bounding box of the point cloud. Other settings are the same. But both of the results are not so good.

Answer 1 · 2023-12-05T07:28:21.000Z

Thank you for the results! I will review the data in more detail

Answer 2 · 2023-12-05T08:21:38.000Z

Sorry to bother you, I fail to reproduce the issues. The results seem OK on my side.

Answer 3 · 2023-12-05T08:23:53.000Z

We have built a docker for this repo, maybe you could run the latest with this environment to see whether it could fix

docker pull hugoycj/instant-angelo
docker run -it hugoycj/instant-angelo

Answer 4 · 2023-12-05T11:49:05.000Z

Thank you so much for the reply. I will try it later.

Answer 5 · 2023-12-05T11:51:01.000Z

By the way, the current results are generated using the neuralangelo-colmap_sparse.yaml configuration. We have temporarily discarded the neuralangelo-colmap_sparse-50k.yaml since we found limited quality improvement and it is less robust than the neuralangelo-colmap_sparse.yaml. For detailed reconstruction, we sincerely recommend the neuralangelo-colmap_dense.yaml which utilizes the dense point cloud from MVSNet or even from other MVS tools like drone2map as a prior.