Open shiba24 opened 1 year ago
Hi, sorry for the delay.
For the real data, we don't have ground-truth RGB images. Therefore, we used synced caterpillar image as a placeholder, as to at least see which view is being rendered in tensorboard.
The view number is from 0 to 1000, corresponding to a full turn around the object, where view 1000=view 0.
In the synthetic data, it is 1s, therefore it is in milliseconds. With the real data, the rotation speed is 45RPM, so view 1000 corresponds to t=1.33 seconds in the real world.
Best, Viktor
Hi, I have two questions regarding the real sequences.
data/real/legocube/train
for example, events and RGB are not aligned. Assume the RGB file names correspond to the millisec unit, (ex.r_00000.png
= 0sec,r_00001.png
= 0.001sec), An example output of the same timestamps from event camera and image is as below and looks not properly aligned:(Please ignore the wrong color of the RGB, it's basically because of my visualizer. What I want to ask is the alignment between frame data and event data.)
plant
,chick
,mic
) look like just legocube. Can you double check if you upload image data correctly?Or am I doing anything wrongly?
Best,
Shintaro