f0ti
Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875
on Monday January 12, 2026 @06:48PM (#46595719)
Einstein is not AGI, and neither the other way around.
Re:Colorize Lidar point clouds with camera images
on Saturday August 17, 2024 @01:03PM (#41275957)
Have been doing something similar to this using image to image translation (XYZ rendered images to RGB space domain). Most of the information is contained in the Z-axis which gives you the height information, e.g. helps to distinguish the grass and buildings color. However I am skeptical if the X and Y is noise and how much spatial information it provides during Conv blocks. Anyone who had previous experience on this?