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

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.

arXiv commentBritish Machine Vision Conference (BMVC) 2018

References in corpus (6)

• WaveNet: A Generative Model for Raw Audio
• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth
• SLAMBench2: Multi-Objective Head-to-Head Benchmarking for Visual SLAM
• UnrealCV: Connecting Computer Vision to Unreal Engine
• UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision

Cited by in corpus (23)

• The Replica Dataset: A Digital Replica of Indoor Spaces
• Navigating the Landscape for Real-time Localisation and Mapping for Robotics and Virtual and Augmented Reality
• A Survey on RGB-D Datasets
• I-Design: Personalized LLM Interior Designer
• ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization
• Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM
• 3D-FUTURE: 3D Furniture shape with TextURE
• 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics
• OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
• MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM
• Fast 3D Indoor Scene Synthesis with Discrete and Exact Layout Pattern Extraction
• Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture
• IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation
• Simultaneous Localization and Mapping Related Datasets: A Comprehensive Survey
• RuDaCoP: The Dataset for Smartphone-based Intellectual Pedestrian Navigation
• E3D: Event-Based 3D Shape Reconstruction
• Furnishing Your Room by What You See: An End-to-End Furniture Set Retrieval Framework with Rich Annotated Benchmark Dataset
• A study of the effect of the illumination model on the generation of synthetic training datasets
• StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation
• End-to-End Optimization of Scene Layout
• Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias
• MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis
• Advanced Mapping Robot and High-Resolution Dataset