We rendered the one million part ABC dataset from Deep Geometry, and open-sourced the data. We also built a fun demo with the following pipeline: CAD > render > caption > embed.
I searched this for "WAGO" and "XT90", so I guess not the same use case. Some hits for "Raspberry Pi", though.
DavidFerris 20 hours ago [-]
This isn't meant to be a commercially useful search engine- just a demonstration. You'll only be able to search for terms that the VLM could directly discern.
From the blog post:
Our search demo proves that it works quite well. As anticipated, text search works well, returning sensible results for even irregular or poorly formed queries. It’s worth mentioning that this is very different from 3D part libraries like Thingiverse or GrabCAD. Search in those repositories requires users to tag or annotate parts with a description, the text of which is used in search. Our system takes only an unnamed part as input, requiring no additional labelling.
sho_hn 20 hours ago [-]
I see, you did an AI demo of captioning and search over captures specifically for complex geometric objects.
I guess my interest was more piqued by the "CAD" part.
bstsb 36 minutes ago [-]
i tried “apples” and got lots of nuts-and-bolts models?
edit: looks like the data is trained from machinery parts. impressive regardless, but i’d add that to the lander
DavidFerris 19 minutes ago [-]
There's a pretty big bias for mechanical engineering components in the dataset- very few organic forms. It's one of the limitations we call out in the dataset card.
There are a few though! Try "dog" or "cookie cutter" for example.
Rendered at 18:57:53 GMT+0000 (Coordinated Universal Time) with Vercel.
Open-sourced dataset: https://huggingface.co/datasets/daveferbear/3d-model-images-...
Blog writeup: https://www.finalrev.com/blog/embedding-one-million-3d-model...
My go-to for CAD files is usually https://grabcad.com/library
I searched this for "WAGO" and "XT90", so I guess not the same use case. Some hits for "Raspberry Pi", though.
From the blog post: Our search demo proves that it works quite well. As anticipated, text search works well, returning sensible results for even irregular or poorly formed queries. It’s worth mentioning that this is very different from 3D part libraries like Thingiverse or GrabCAD. Search in those repositories requires users to tag or annotate parts with a description, the text of which is used in search. Our system takes only an unnamed part as input, requiring no additional labelling.
I guess my interest was more piqued by the "CAD" part.
edit: looks like the data is trained from machinery parts. impressive regardless, but i’d add that to the lander
There are a few though! Try "dog" or "cookie cutter" for example.