Questions about gt_RTs, why negative?

hughw19 / NOCS_CVPR2019

[CVPR2019 Oral] Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation on Python3, Tensorflow, and Keras

https://geometry.stanford.edu/projects/NOCS_CVPR2019/

Other

454 stars 72 forks source link

Questions about gt_RTs, why negative? #76

Open kszpxxzmc opened 1 year ago

kszpxxzmc commented 1 year ago

I've noticed that many gt_RTs have a negative second column, for example [[ 0.02939445 -0.00273414 0.13457581 -0.03205877] [-0.0970588 -0.09587024 0.01925211 0.04699949] [ 0.09326153 -0.09891198 -0.02238002 1.03801286] [ 0. 0. 0. 1. ]] This means that the model is inverted up and down, but the picture doesn't actually show this. May I ask why this is?