YunzhuLi / VisGel

[CVPR 2019] Connecting Touch and Vision via Cross-Modal Prediction
http://visgel.csail.mit.edu/
70 stars 17 forks source link

The selection of reference visual and tactile images #3

Open xiaoen0 opened 1 year ago

xiaoen0 commented 1 year ago

How the reference visual and tactile images in each sample are selected from the collected data? I'm not quite sure about this.

YunzhuLi commented 1 year ago

Please refer to the details of the reference images in Section 4.2, "Improving Photorealism and Accuracy".