InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset

TL;DR

InteriorNet is a large-scale, photo-realistic indoor scene dataset created from professional interior designs and assets, supporting various sensors and used for benchmarking SLAM algorithms.

Contribution

It introduces a highly detailed, scalable synthetic indoor dataset with realistic rendering and sensor data, surpassing existing datasets in realism and variability.

Findings

Benchmarking results for SLAM algorithms demonstrate dataset utility.

High realism and variability improve training and evaluation.

Supports multiple camera types and inertial measurements.

Abstract

Datasets have gained an enormous amount of popularity in the computer vision community, from training and evaluation of Deep Learning-based methods to benchmarking Simultaneous Localization and Mapping (SLAM). Without a doubt, synthetic imagery bears a vast potential due to scalability in terms of amounts of data obtainable without tedious manual ground truth annotations or measurements. Here, we present a dataset with the aim of providing a higher degree of photo-realism, larger scale, more variability as well as serving a wider range of purposes compared to existing datasets. Our dataset leverages the availability of millions of professional interior designs and millions of production-level furniture and object assets -- all coming with fine geometric details and high-resolution texture. We render high-resolution and high frame-rate video sequences following realistic trajectories while supporting various camera types as well as providing inertial measurements. Together with the release of the dataset, we will make executable program of our interactive simulator software as well as our renderer available at https://interiornetdataset.github.io. To showcase the usability and uniqueness of our dataset, we show benchmarking results of both sparse and dense SLAM algorithms.