Loading video...

Video Failed to Load

Go Home

I’ve created procedural generators of ICs and connectors using geometry nodes. Due to the large number of different packages of ICs and connectors, it might be better to generate their models as and when needed rather than storing an unlimited number of unique 3D models. Also using the new...

50,726 views • 1 year ago •via X (Twitter)

11 Comments

Seve's profile picture
Seve1 year ago

This is awesome!! We’re building something similar (a large 3d electronics library with parameterized models) Would love to collaborate!!

Rainmaker's profile picture
Rainmaker2 years ago

In this free Substack post I share code for several machine learning models and engage in hyperparameter tuning that yields a model that delivers superior returns in the Gold market.

John's profile picture
John1 year ago

This system breaks down because many new ICs have unique footprints and models, so you will still need a library system nonetheless. Besides that, it looks good

Adam Raudonis's profile picture
Adam Raudonis1 year ago

What you do is so cool!!!

木子不是木子狸's profile picture
木子不是木子狸1 year ago

That's what I neeeed!

Dean Sheppard's profile picture
Dean Sheppard1 year ago

I’m using manufacturer 3D models to verify how they fit the actual footprint. Creating something based on a possibly wrong footprint goes against logic imho.

Michael Rangen's profile picture
Michael Rangen1 year ago

I want to be good at Blender one day, just so I can leverage all the cool tools you’re building. Keep up the great work!

neoCortez's profile picture
neoCortez1 year ago

Looks awesome, been wanting to dive further into geometry nodes!

huseyin sağır's profile picture
huseyin sağır1 year ago

Süper.

navzz's profile picture
navzz1 year ago

Cool

Sohan Basak e/code's profile picture
Sohan Basak e/code1 year ago

Blender for CAD!

Related Videos

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 views • 3 years ago