junzhezhang

Updated the PR as per required on 09 Nov meeting, focused on correctness and code readability.

Replaced the strings with structs in Append function as per requested, updated in branch vd2. New PR could not be created to Apache master, so it was created to my...

The quantitative results are in 3D IoU but we use 2D estimated mask during inference; the geometric performance is to some extent bottlenecked by the pre-trained ConvMesh performance - that...

@kkyi10 Hi, I would like to clarify that, Table 1 is indeed in 2D IoU (measured between our output mask and GT mask), whereas Table 3 is in 3D IoU...

Hi, Perhaps it is due to higher resources required than your CUDA can provide. You may want to explore reducing the sampling points of texture loss from 8192 to say...