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

By Wenbin Li, Sajad Saeedi, John McCormac, R. Clark, Dimos Tzoumanikas, Qing Ye, Yuzhong Huang, R. Tang, Stefan Leutenegger. 2018

256 citations recorded by the source corpus.

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 this https URL. To showcase the usability and uniqueness of our dataset, we show benchmarking results of both sparse and dense SLAM algorithms.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding (2020, methodology): “View Sampling Methods for Synthetic Scenes Existing view sampling methods for synthetic scenes include: sampling views uniformly at random [71, 79]; using data-driven methods to generate realistic camera jitter [41]; and using semantic segmentation information to match the distribution of semantic c”
MSeg: A Composite Dataset for Multi-Domain Semantic Segmentation (2020, methodology): “INTERIORNET [58] Indoor (Synthetic) 20,000,000 We do not use synthetic data.”
ESIM: an Open Event Camera Simulator (2018, methodology): “To the best of the author’s knowledge, [10] and [24] are the only simulators that attempt to simulate an event camera accurately.”
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences (2019, methodology): “For indoor environments, there are several datasets [48, 46, 24, 3, 11, 35, 32, 12] available, which are mainly recorded using RGB-D cameras or synthetically generated.”
Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling (2019, background): “InteriorNet [15] Professional n/a Photo-realistic O U S”
MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM (2018, methodology): “We also tested our method within a fully controlled synthetic environment using photo-realistic rendering and trajectory simulation [24].”
Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM (2019, background): “Recent progress in random scene generation and photo-realistic rendering [6][7] makes it theoretically possible to synthesize scene changes for lifelong SLAM, but it would be difﬁcult to model realistic changes as in natural lives.”
3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics (2020, methodology): “With datadriven and learning-based approaches receiving more and more attention in recent years, there has been a steady accumulation of indoor scene datasets [27, 36, 43, 4, 19, 6, 9, 18, 23, 49, 24] to drive the deep learning revolution that has”
OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets (2020, background): “Synthetic datasets provide an alternative [38, 49, 31], but prior ones are limited with respect to rendering arbitrary data [31], scene layout [38], material [49], or baselines [42], as summarized in Table 1.”
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets (2020, background): “However, most of these datasets do not offer the ability to render arbitrary ground truth data [27], or do not have real-world scene layout [33] or material appearance [42].”
3D-FUTURE: 3D Furniture Shape with TextURE (2020, methodology): “The works most closely related to ours are InteriorNet (Li et al., 2018) and Structured3D (Zheng et al.”