“ShapeCoder: Discovering Abstractions for Visual Programs From Unstructured Primitives” by Jones, Guerrero, Mitra and Ritchie

  • ©R. Kenny Jones, Paul Guerrero, Niloy J. Mitra, and Daniel Ritchie

Conference:


Type(s):


Title:

    ShapeCoder: Discovering Abstractions for Visual Programs From Unstructured Primitives

Session/Category Title:   Geometric Abstractions: Not Just for Cubists


Presenter(s)/Author(s):


Moderator(s):



Abstract:


    ShapeCoder automatically discovers abstraction functions, and infers visual programs that use these abstractions, to compactly explain an input dataset of shapes represented with unstructured primitives. Discovered abstractions capture common patterns (both structural and parametric) so that programs rewritten with these abstractions are more compact and expose fewer degrees of freedom.


Additional Images:

©R. Kenny Jones, Paul Guerrero, Niloy J. Mitra, and Daniel Ritchie

Overview Page: