Unable to Create DepthMaps for Resolution Level0 with GPU Docker.

[vivekmistry]

With latest OpenMVS Dev Branch, had successfully generated DepthMaps for Resolution Level1 with CPU & GPU Docker. Now, for Reoslution Level0 the DepthMaps are generated with CPU Docker but fails with GPU Docker with following error:

Error Message: terminate called after throwing an instance of ‘std::bad_alloc’ what(): std::bad_alloc

Below are our InfraStructure details:

Cloud: AWS EC2 Instance Type: g4dn.12xlarge(48vCPus and 192GB RAM) OS: Linux OpenMVS Docker: Yes GPU Type: NVIDIA T4 GPUs (16GB GPU RAM)

[cdcseacave]

Reoslution Level0 can be anything, it just means the original image is not downscaled so what is the original image resolution?

[vivekmistry]

The Original Image Resolution is 19470*9062.

[cdcseacave]

that explains it, the GPU run OOM in order to process such high resolution a divide and conquer approach needs to be implemented; I can help you with that, but in order to be able to make some time for it pls consider a donantion

[ghost]

Would a similar divide and conquer approach be implemented for fusing depth maps?

[cdcseacave]

yes