MIT AI model: GenCAD: 2D => 3D (image => CAD)

Guri Singh on X: "🚨BREAKING: MIT just dropped an AI model that converts photos into fully editable CAD programs and it quietly kills the $150/hour CAD modeling industry. It's called GenCAD. You give it an image. It gives you the complete parametric command sequence lines, arcs, extrusions ready https://t.co/RyufCrWLeY" / X

You give it an image. It gives you the complete parametric command sequence lines, arcs, extrusions ready for manufacturing. Not meshes. Not point clouds. Actual editable CAD. - Autoregressive transformers + diffusion models for image-to-CAD translation - Outperforms every existing method on unconditional and 

conditional CAD generation - Retrieves matching designs from 7K+ CAD databases using just a photo - Trained on 840K+ images - Generates multiple valid designs from a single input

ferdous-alam/GenCAD @GitHub

Vectorizing images for OpenSCAD is best achieved by converting raster images (PNG/JPG) into vector SVG files using tools like Inkscape, then importing them with import() and linear_extrude(). The most common workflow involves tracing bitmaps in Inkscape to create paths, saving as SVG, and importing the vector data to produce 3D objects.

 
Recommended Workflow (Inkscape to OpenSCAD) Trace Bitmap: 

Open your image in Inkscape. Select the image and go to Path > Trace Bitmap to create a vector outline.
Clean Up: Delete the original raster image, leaving only the vector paths. Ensure the image is black and white for the best result.
Save as SVG: Save the file as a plain SVG or use a specialized extension to save as a DXF or SCAD file.
Import in OpenSCAD: Use the following command in OpenSCAD:

Watch a detailed tutorial on YouTube about the Bitmap2Vector process.

Read an Instructables guide on converting 2D images to 3D objects.