RebrickNet learns by looking at images of LEGO parts and discovering the features that make each part unique. AIs like RebrickNet use machine

RebrickNet - LEGO Part detector

submited by

Style Pass

2024-10-26 23:30:03

RebrickNet learns by looking at images of LEGO parts and discovering the features that make each part unique. AIs like RebrickNet use machine learning to discover relevant features. This learning process requires millions of images under a wide variety of lighting conditions.

Submitting images is far easier than videos. Simply grab a bunch (~ 10 to 20) of a single part type and place them on a flat surface. You can take many photos of the parts (aim for at least 10), shuffling them in between each time. The background can be anything as long as it doesn't contain LEGO images or other parts. Using a variety of backgrounds helps too.

For each part you submit, we need one video per part orientation. So, for each possible orientation that a part might be seen, take a short 10-20 sec video that consists of one whole rotation of the part in that orientation.

For example, the 3001 part below requires 3 videos per color. The 4th orientation may also be submitted in this case but is not really necessary as it will almost never appear in that orientation.