6 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…
MiGumi: Making Tightly Coupled Integral Joints Millable
Aditya Ganeshan, Kurt Fleischer, Wenzel Jakob +4
Traditional integral wood joints, despite their strength, durability, and elegance, remain rare in modern workflows due to the cost and difficulty of manual fabrication. CNC millin…
ProcTex: Consistent and Interactive Text-to-texture Synthesis for Part-based Procedural Models
Ruiqi Xu, Zihan Zhu, Ben Ahlbrand +2
Recent advances in generative modeling have driven significant progress in text-guided texture synthesis. However, current methods focus on synthesizing texture for single static 3…
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…