COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
Quick Answer
COrigami is an AI-driven pipeline that generates crease patterns for origami from natural language, addressing geometric and aesthetic challenges in computational origami.
Quick Take
It integrates reinforcement learning with aesthetic evaluation to assist artists in creating visually recognizable and flat-foldable designs.
Key Points
- COrigami generates crease patterns through a semantic stick figure and base packing.
- The pipeline refines designs using reinforcement learning and autonomous aesthetic evaluation.
- It serves as a collaborative assistant for human artists in origami design.
- The system addresses multi-objective physical constraints in artistic creation.
Paper Resources
📖 Reader Mode
~2 min readAuthors:Tom Zahavy, Shaobo Hou, Thomas Tumiel, James Doran, Francesco Faccio, Xidong Feng, Alex Havrilla, Igor Khytryi, Chenglei Li, Lisa Schut, Vivek Veeriah, Arijan Abrashi, Michał Kosmulski, Robert J. Lang, Nick Robinson, Brandon Wong, Marcus Chiam, Gloria Fang, Satinder Singh
Abstract:While generative AI has achieved remarkable success in solving problems with verifiable solutions, generating physical art that satisfies both strict geometric constraints and subjective visual aesthetics remains a challenge. This paper presents an approach to tackle these difficulties in the domain of computational origami, a mathematically rigid environment that grounds artistic design within the equations of flat foldability. We present COrigami, an end-to-end AI-driven pipeline that assists the design cycle by generating crease patterns from natural language. Our pipeline involves generating a semantic stick figure, computing a base packing, solving for a flat-foldable crease pattern, shaping the flat-folded crease pattern, and refining the generated model using reinforcement learning driven by an autonomous aesthetic evaluation loop. Our system acts as a highly effective collaborative assistant, generating structural starting points that human artists can further expand and shape. By integrating algorithmic optimisation with autonomous aesthetic critique, this work demonstrates how AI systems can satisfy multi-objective physical constraints to enable reliable, mathematically grounded co-creativity.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.26299 [cs.AI] |
| (or arXiv:2606.26299v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.26299 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tom Zahavy [view email]
[v1]
Wed, 24 Jun 2026 18:43:24 UTC (9,638 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.