Tesserae3d: A Benchmark for Tesserae Semantic Segmentation in 3d Point Clouds

Abstract

Abstract. 3D point cloud of mosaic tesserae is used by heritage researchers, restorers and archaeologists for digital investigations. Information extraction, pattern analysis and semantic assignment are necessary to complement the geometric information. Automated processes that can speed up the task are highly sought after, especially new supervised approaches. However, the availability of labelled data necessary for training supervised learning models is a significant constraint. This paper introduces Tesserae3D, a 3D point cloud benchmark dataset for training and evaluating machine learning models, applied to mosaic tesserae segmentation. It is a publicly available, very high density and coloured dataset, accompanied by a standard multi-class semantic segmentation baseline. It consists of about 502 million points and contains 11 semantic classes covering a wide range of tesserae types. We propose a semantic segmentation baseline building on radiometric and covariance features fed to ensemble learning methods. The results delineate an achievable 89% F1-score and are made available under https://github.com/akharroubi/Tesserae3D, providing a simple interface to improve the score based on feedback from the research community.

Classification of Large-Scale Mobile Laser Scanning Data in Urban Area with LightGBM

“…Decision tree ensemble learning has previously been performed for 3D PCC, based on the technique of bagging [14,22] or boosting [20]. RF [28]-a bagging-based ensemble of decision trees, which is based on a combination of tree scores from randomly created multiple decision trees-especially comes forward among them [15] and has become a popular choice of ML classifier in 3D PCC [14,21,22], and even considered as a baseline method in many benchmark datasets, such as in Kölle et al [52] and Kharroubi et al [53]. Gradient-boosting machines [54], however, construct a strong learner from weak learners iteratively, which is based on improving the scores according to the previous iteration.…”