Computer Vision

A Gaming GPU Helps Crack the Code on a Thousand-Yr Cultural Dialog

July 11, 2025
roosho

Ceramics — the common-or-garden mixture of earth, fireplace and artistry — have been a part of a world dialog for millennia.

From Tang Dynasty commerce routes to Renaissance palaces, from museum vitrines to high-stakes public sale flooring, they’ve carried tradition throughout borders, evolving into standing symbols, commodities and items of contested historical past. Their worth has been formed by aesthetics and economics, empire and, now, expertise.

This determine visualizes 20 consultant Chinese language ceramic craftsmanship kinds throughout seven historic durations, starting from the Tang Dynasty (618–907 AD) to the Fashionable period (1913–2025). These kinds, together with kiln-specific classes and ornamental methods, have been chosen for his or her historic significance and visible distinctiveness for the AI’s coaching dataset. Courtesy of Yanfeng Hu, Siqi Wu, Zhuoran Ma and Si Cheng.

In a lab at College Putra Malaysia, that legacy meets silicon. Researchers there, alongside colleagues at UNSW Sydney, have constructed an AI system that may classify Chinese language ceramics and predict their worth with uncanny precision. The instrument makes use of deep studying to research ornamental motifs, shapes and kiln-specific craftsmanship. It predicts worth classes primarily based on actual public sale knowledge from establishments like Sotheby’s and Christie’s, reaching take a look at accuracy as excessive as 99%.

Past kind, the AI additionally analyzes the intricate ornamental patterns discovered on Chinese language ceramics, that are organized into six main classes: plant patterns, animal motifs, landscapes, human figures, crackled glaze patterns and geometric designs. The system annotates photos on the class degree primarily based on probably the most visually dominant sample varieties. Courtesy of Yanfeng Hu, Siqi Wu, Zhuoran Ma, and Si Cheng.

It’s all powered by an NVIDIA GeForce RTX 3090, a consumer-grade GPU beloved by players, explains Siqi Wu, one of many researchers behind the mission. Not an information heart, not specialised industrial {hardware}, simply the identical chip pushing body charges for players having fun with Cyberpunk 2077 and Alan Wake 2 internationally.

The motivation is as outdated because the commerce routes these ceramics as soon as traveled: entry, however on this case, entry to experience somewhat than materials items.

The AI system employs a typological classification system for ceramic vessel shapes, primarily based on modular morphological components just like the bottle neck, deal with, shoulder, spout, physique and base. This method permits for detailed evaluation and classification of shapes comparable to bottles, jars, plates, bowls, cups, pots and washbasins. Courtesy of Yanfeng Hu, Siqi Wu, Zhuoran Ma and Si Cheng.

“Artifact pricing and relationship nonetheless closely depend on professional judgment,” Wu stated. That experience stays elusive for youthful collectors, smaller establishments and digital archive initiatives. Wu’s staff goals to alter that by making cultural appraisal extra goal, scalable and accessible to a wider viewers.

It doesn’t cease at classification. The system pairs its YOLOv11-based detection mannequin with an algorithm that realized market worth instantly from years of real-world public sale outcomes. In a single take a look at, the AI assessed a Ming Dynasty artifact at roughly 30% beneath its remaining hammer worth. It’s a reminder that even in an business steeped in custom, algorithms can provide new views.

These views don’t simply quantify heritage, they lengthen the dialog. The staff is already exploring AI for different types of cultural visible heritage, from Cantonese opera costumes to historic murals.

For now, a graphics card constructed for gaming is parsing centuries of workmanship and coming into one of many world’s oldest and most world debates: what makes one thing precious?