Subhransu S. Bhattacharjee

Same here with Ubuntu 22.04 LTS

> It seems there is no need to run whole sfm with known camera intrinsic and extrinsic. You just need to run BA on it. Check https://github.com/colmap/pycolmap/blob/b6627db2266f098c21c3d7e4b7844b4b90d8e02d/pycolmap/pipeline/sfm.h#L95 Yes, I did...

Thanks a lot. Right now I am looking for non-neural approaches because it does not make sense to compare it with deep features. On Mon, Apr 22, 2024 at 5:40 ...

Hi, @jytime you seem to have performed COLMAP reconstruction for RealEstate10k dataset for your work. Can you provide any guidance on how it performs and what settings you end up...

Just to clarify, without deep learning enhancements, the only approach you found useful is running the COLMAP automatic reconstruction (complete pipeline) which is messy but works for all the scenes...

Nope not working, am I doing something wrong? 

I have a more general question, NeRFs which are not explicitly depth supervised, often seem to output depth values differerent from those using the same camera poses (these values seem...

I faced the same issue even on a Linux machine go with xFormers. The issue is that there is an internal dependency on the backbone which requires some version of...

Pretty good on visualisation. @LiheYoung is it possible to confirm that the depths say 4.54 is in metres and there are no additional scales at play?

I will update with my code right here, just waiting for the confirmation of the author on the correctness of scale. On Fri, 26 Jan, 2024, 11:25 pm shizurumaya, ***@***.***>...