search

skhadem / 3D-BoundingBox

PyTorch implementation for 3D Bounding Box Estimation Using Deep Learning and Geometry
MIT License
435 stars 96 forks source link

assumption in the paper #7

Closed maxwellfrom closed 4 years ago

maxwellfrom commented 4 years ago

Hi I have a question. In the paper 3D Bounding Box Estimation Using Deep Learning and Geometry, there is a assumption that 3D bounding box fits tightly into 2D detection window requires that each side of the 2D bounding box to be touched by the projection of at least one of the 3D box corners. I have tested your codes, it seems that you have not considered that. Could you please have a discussion?

skhadem commented 4 years ago

Hi. Yes I actually have used this fact in creating all possible constraints here. The idea is to check all possible configurations of which side is touched, and then the one with the least re projection error is used. I would love to provide more details.

skhadem commented 4 years ago

Closing for inactivity