Saved in:
Bibliographic Details
Main Authors: Zhai, Ziyu, Li, Siyou, Shao, Juexi, Yu, Juntao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.06641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909022909628416
author Zhai, Ziyu
Li, Siyou
Shao, Juexi
Yu, Juntao
author_facet Zhai, Ziyu
Li, Siyou
Shao, Juexi
Yu, Juntao
contents Developing ceramic glazes is a costly, time-consuming process of trial and error due to complex chemistry, placing a significant burden on independent artists. While recent advances in multimodal AI offer a modern solution, the field lacks the large-scale datasets required to train these models. We propose GlazyBench, the first dataset for AI-assisted glaze design. Comprising 23,148 real glaze formulations, GlazyBench supports two primary tasks: predicting post-firing surface properties, such as color and transparency, from raw materials, and generating accurate visual representations of the glaze based on these properties. We establish comprehensive baselines for property prediction using traditional machine learning and large language models, alongside image generation benchmarks using deep generative and large multimodal models. Our experiments demonstrate promising yet challenging results. GlazyBench pioneers a new research direction in AI-assisted material design, providing a standardized benchmark for systematic evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06641
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GlazyBench: A Benchmark for Ceramic Glaze Property Prediction and Image Generation
Zhai, Ziyu
Li, Siyou
Shao, Juexi
Yu, Juntao
Artificial Intelligence
Computer Vision and Pattern Recognition
Developing ceramic glazes is a costly, time-consuming process of trial and error due to complex chemistry, placing a significant burden on independent artists. While recent advances in multimodal AI offer a modern solution, the field lacks the large-scale datasets required to train these models. We propose GlazyBench, the first dataset for AI-assisted glaze design. Comprising 23,148 real glaze formulations, GlazyBench supports two primary tasks: predicting post-firing surface properties, such as color and transparency, from raw materials, and generating accurate visual representations of the glaze based on these properties. We establish comprehensive baselines for property prediction using traditional machine learning and large language models, alongside image generation benchmarks using deep generative and large multimodal models. Our experiments demonstrate promising yet challenging results. GlazyBench pioneers a new research direction in AI-assisted material design, providing a standardized benchmark for systematic evaluation.
title GlazyBench: A Benchmark for Ceramic Glaze Property Prediction and Image Generation
topic Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.06641