3D scene reconstruction from 2D images is an important task in computer graphics. Unfortunately, existing datasets and benchmarks focus on idealized synthetic data or meticulously captured realistic data. Such benchmarks fail to capture the inherent complexities found in newly acquired real-world scenes. In such scenes, the background is often dynamic, and due to the widespread use of cell phone cameras, there may be discrepancies in aspects such as white balance. To address this gap, we present HuSc3D, a novel dataset specifically designed for rigorous benchmarking of 3D reconstruction models under realistic acquisition challenges. Our dataset features six highly detailed, entirely white sculptures characterized by intricate perforations and minimal textural variation. Furthermore, the number of images per scene varies significantly, introducing the additional challenge of limited training data for some instances alongside scenes with a standard number of views. By evaluating 3D reconstruction methods on this diverse dataset, we demonstrate HuSc3D’s ability to effectively distinguish between model performances, particularly highlighting the sensitivity of methods to fine geometric details, color ambiguity, and varying data availability—limitations often masked by more conventional datasets. The project page is available here.
Authors: Weronika Smolak-Dyżewska, Dawid Malarz, Grzegorz Wilczyński, Rafał Tobiasz, Joanna Waczyńska, Piotr Borycki, Przemysław Spurek