BUDA.ART: A Multimodal Content-Based Analysis and Retrieval System for Buddha Statues

TL;DR

BUDA.ART is a multimodal system that enables researchers to explore and analyze a large archive of Buddha statues using image, 3D scans, and metadata, focusing on facial features for content-based retrieval.

Contribution

The paper presents BUDA.ART, a novel multimodal retrieval system integrating CBIR and classical techniques for Buddha statues, including facial embeddings and 3D analysis.

Findings

Successfully built an archive of 50,000 images and 3D scans.

Enabled on-site, mobile search and exploration of statue similarities.

Provided visualization tools and 3D analysis for detailed examination.

Abstract

We introduce BUDA.ART, a system designed to assist researchers in Art History, to explore and analyze an archive of pictures of Buddha statues. The system combines different CBIR and classical retrieval techniques to assemble 2D pictures, 3D statue scans and meta-data, that is focused on the Buddha facial characteristics. We build the system from an archive of 50,000 Buddhism pictures, identify unique Buddha statues, extract contextual information, and provide specific facial embedding to first index the archive. The system allows for mobile, on-site search, and to explore similarities of statues in the archive. In addition, we provide search visualization and 3D analysis of the statues