5 papers
ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models
R. Kenny Jones, Paul Guerrero, Niloy J. Mitra +1
We present ShapeLib, the first method that uses the priors of Large Language Models (LLMs) to design libraries of programmatic 3D shape abstractions. Our system accepts two forms o…
Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Search
Maxim Gumin, Do Heon Han, Seung Jean Yoo +6
Synthesizing 3D scenes from open-vocabulary text descriptions is a challenging, important, and recently-popular application. One of its critical subproblems is layout generation: g…
Imperative vs. Declarative Programming Paradigms for Open-Universe Scene Generation
Maxim Gumin, Do Heon Han, Seung Jean Yoo +5
Current methods for generating 3D scene layouts from text predominantly follow a declarative paradigm, where a Large Language Model (LLM) specifies high-level constraints that are…
PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples
Junyu Liu, R. Kenny Jones, Daniel Ritchie
We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful…
Learning to Edit Visual Programs with Self-Supervision
R. Kenny Jones, Renhao Zhang, Aditya Ganeshan +1
We design a system that learns how to edit visual programs. Our edit network consumes a complete input program and a visual target. From this input, we task our network with predic…