VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery
This work addresses the challenge of analyzing ancient Greek pottery for digital heritage preservation, but it is incremental as it adapts existing methods to a new domain-specific dataset.
The paper tackles the problem of data scarcity and insufficient domain knowledge for Vision-Language Models (VLMs) in specialized cultural heritage domains like 3D vase artifacts, resulting in a 12.8% improvement on R@1 metrics and a 6.6% improvement on lexical similarity compared to previous state-of-the-art on their new dataset.
Vision-Language Models (VLMs) have achieved significant progress in multimodal understanding tasks, demonstrating strong capabilities particularly in general tasks such as image captioning and visual reasoning. However, when dealing with specialized cultural heritage domains like 3D vase artifacts, existing models face severe data scarcity issues and insufficient domain knowledge limitations. Due to the lack of targeted training data, current VLMs struggle to effectively handle such culturally significant specialized tasks. To address these challenges, we propose the VaseVQA-3D dataset, which serves as the first 3D visual question answering dataset for ancient Greek pottery analysis, collecting 664 ancient Greek vase 3D models with corresponding question-answer data and establishing a complete data construction pipeline. We further develop the VaseVLM model, enhancing model performance in vase artifact analysis through domain-adaptive training. Experimental results validate the effectiveness of our approach, where we improve by 12.8% on R@1 metrics and by 6.6% on lexical similarity compared with previous state-of-the-art on the VaseVQA-3D dataset, significantly improving the recognition and understanding of 3D vase artifacts, providing new technical pathways for digital heritage preservation research. Code: https://github.com/AIGeeksGroup/VaseVQA-3D. Website: https://aigeeksgroup.github.io/VaseVQA-3D.