Multi-sensor large-scale dataset for multi-view 3D reconstruction

TL;DR

This paper introduces a comprehensive multi-sensor dataset with diverse scenes, modalities, and lighting conditions to advance multi-view 3D surface reconstruction research and algorithm development.

Contribution

It provides a large-scale, multi-modal dataset with extensive scene diversity and challenging material properties for training and evaluating 3D reconstruction algorithms.

Findings

Dataset includes 1.4 million images from 107 scenes.

Data covers multiple sensors, resolutions, and lighting conditions.

Designed to improve algorithm robustness and evaluation.

Abstract

We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial cameras, and structured-light scanner. The scenes are selected to emphasize a diverse set of material properties challenging for existing algorithms. We provide around 1.4 million images of 107 different scenes acquired from 100 viewing directions under 14 lighting conditions. We expect our dataset will be useful for evaluation and training of 3D reconstruction algorithms and for related tasks. The dataset is available at skoltech3d.appliedai.tech.