segmentation-driven-pose icon indicating copy to clipboard operation
segmentation-driven-pose copied to clipboard

Published 20 hours ago • verified publisher icon cvlab-epfl

About Occluded-LINEMOD training data

Open alen0216056 opened this issue 5 years ago • 1 comments

Hi, Do you generate synthetic data by rendering the provided models? or only using the central objects in LINEMOD scenes?

For each epoch, how many training images do you use? 20k samples mentioned in the paper?

Thanks.

alen0216056 avatar Aug 14 '19 09:08 alen0216056

We only use the central objects in LINEMOD, and generate 20K sample images from the central objects by random combinations.

YinlinHu avatar Aug 14 '19 17:08 YinlinHu