Sentence to Object

A Python pipeline that converts inputted sentences into 3D printable mesh objects by mapping the token embedding relationships into geometric form. Tokens become mesh vertices and mesh edges represent the vector length between tokens in the sentence. Sentences are embedded in high-dimensional vector space, reduced to 3D coordinates via shared-reference PCA, and processed through various mesh surface-generation methods. Methods include: Delaunay Triangulation, Voronoi, swept tube, adaptive alpha. The shape is defined by physical representation of the LLM interpretation of the sentence. 


3D printed object s from these inputed words:

“Sprattling was one of the lucky audience members who snagged a coveted complimentary ticket with the help of her cousin, an artist who participated in the monthlong International Jazz Day festivities across the city. More than half of the roughly 3,000 seats were reserved for local creatives, students, educators and the general public, who registered online for a chance to receive admission.” (text taken from an email from WNYC)

3D printed objects. Mesh surface generation methods (right to left): adaptive alpha shape, Delauney Triangulation, Vornoi, sweep tube



Preview generated from pipeline. It shows the 3d mesh object with the words (tokens) mapped on to the objects. 
Video of adaptive alpha shape object




Slideshow of project for showcase presentation: