Diceplay: A Modular Canvas for Physical Image Composition
Diceplay, a modular physical canvas for abstract visual composition. Diverse abstract designs automatically generated by our optimization framework are physically realized using a low-power, LED-enabled dice display, which can be reconfigured through changes in dice orientation and dynamically updated via programmable color.
Abstract
We present Diceplay, a modular physical display for abstract visual composition built from a grid of identical dice. Each die has six faces with distinct geometric primitives, and images emerge through the placement and orien tation of the dice. While this medium enables reusable and reconfigurable physical imagery, it poses a challenging design problem: images must be expressed through discrete, extremely low-resolution abstractions, making manual authoring difficult. To address this challenge, we introduce a computational design system that automatically generates Diceplay configurations from text prompts. Our key technical contribution is a grammar-based for mulation that relaxes this discrete design space into a smooth optimization landscape, enabling gradient-based optimization using score distillation sampling. We show that our approach consistently produces meaningful abstractions for this medium, whereas state-of-the-art smoothing techniques fail in this extremely challenging regime. We demonstrate our method across a range of prompts and fabricated examples, showing how computationally generated abstractions can be realized as physical visual artifacts.
Fast Forward
Demo
Citation
@inproceedings{kodnongbua2026diceplay,
author = {Kodnongbua, Milin and Zhang, Zihan and Xiao, Shishi and Li, Vivian and Robertson, Heather and Chen, Rulin and Laidlaw, David and Schulz, Adriana},
title = {Diceplay: A Modular Canvas for Physical Image Composition},
year = {2026},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {We present Diceplay, a modular physical display for abstract visual composition built from a grid of identical dice. Each die has six faces with distinct geometric primitives, and images emerge through the placement and orientation of the dice. While this medium enables reusable and reconfigurable physical imagery, it poses a challenging design problem: images must be expressed through discrete, extremely low-resolution abstractions, making manual authoring difficult. To address this challenge, we introduce a computational design system that automatically generates Diceplay configurations from text prompts. Our key technical contribution is a grammar-based formulation that relaxes this discrete design space into a smooth optimization landscape, enabling gradient-based optimization using score distillation sampling. We show that our approach consistently produces meaningful abstractions for this medium, whereas state-of-the-art smoothing techniques fail in this extremely challenging regime. We demonstrate our method across a range of prompts and fabricated examples, showing how computationally generated abstractions can be realized as physical visual artifacts.},
booktitle = {SIGGRAPH 2026 Conference Papers},
numpages = {11},
location = {Los Angeles, CA, USA},
keywords = {optimization, fabrication, shape grammar},
preview = {2026-diceplay.png},
html = {/publications/diceplay},
pdf = {/assets/papers/SIG-2026-DicePlay.pdf}
}