jianingwei

Results 5 comments of jianingwei

The camera tracks are collected as ARKit metadata during our video camera.

You can also refer to Sec 5.2 of our paper https://arxiv.org/pdf/2012.09988.pdf for our models. On Wed, Jun 2, 2021 at 2:44 PM Adel Ahmadyan ***@***.***> wrote: > A good starting...

You can fit a 2D bounding box to the projections of the 3D bounding box vertices.

I'm unaware of an easy way to find the tight green bounding box from the 3D bounding box. Alternatively you can find a rotated bounding box that's fits the object...

The uuu file format is probably a special one for encryption purposes. Adel, do you have more information around this?