IVL-SYNTHSFM-v2: A synthetic dataset with exact ground truth for the evaluation of 3D reconstruction pipelines

Davide Marelli; Simone Bianco; Gianluigi Ciocca

doi:10.1016/j.dib.2019.105041

IVL-SYNTHSFM-v2: A synthetic dataset with exact ground truth for the evaluation of 3D reconstruction pipelines

Data Brief. 2019 Dec 23:29:105041. doi: 10.1016/j.dib.2019.105041. eCollection 2020 Apr.

Authors

Davide Marelli¹, Simone Bianco¹, Gianluigi Ciocca¹

Affiliation

¹ DISCo-Department of Informatics, Systems and Communication, University of Milano - Bicocca, viale Sarca 336, 20126, Milano, Italy.

Abstract

This article presents a dataset with 4000 synthetic images portraying five 3D models from different viewpoints under varying lighting conditions. Depth of field and motion blur have also been used to generate realistic images. For each object, 8 scenes with different combinations of lighting, depth of field and motion blur are created and images are taken from 100 points of view. Data also includes information about camera intrinsic and extrinsic calibration parameters for each image as well as the ground truth geometry of the 3D models. The images were rendered using Blender. The aim of this dataset is to allow evaluation and comparison of different solutions for 3D reconstruction of objects starting from a set of images taken under different realistic acquisition setups.

Keywords: 3D reconstruction; Blender; Realistically rendered images; Structure from Motion (SfM).