InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset
InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset
复制标题
DOI：
--
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Wenbin Li;Sajad Saeedi;J. McCormac;R. Clark;Dimos Tzoumanikas;Qing Ye;Yuzhong Huang;R. Tang;Stefan Leutenegger
中科院分区：
文献类型：
--
作者：
Wenbin Li;Sajad Saeedi;J. McCormac;R. Clark;Dimos Tzoumanikas;Qing Ye;Yuzhong Huang;R. Tang;Stefan Leutenegger
数据集在计算机视觉社区中获得了极大的普及，从基于深度学习的方法的训练和评估到同步定位和映射（SLAM）的基准测试。毫无疑问，合成图像具有巨大的潜力，由于可扩展性方面的数据量，而无需繁琐的手动地面实况注释或测量。在这里，我们提出了一个数据集，其目的是提供更高程度的照片现实主义，更大的规模，更多的可变性，以及服务于更广泛的目的相比，现有的数据集。我们的数据集利用了数百万专业室内设计和数百万生产级家具和对象资产的可用性-所有这些都具有精细的几何细节和高分辨率纹理。我们呈现高分辨率和高帧率的视频序列，同时支持各种相机类型以及提供惯性测量的逼真轨迹。随着数据集的发布，我们将使我们的交互式模拟器软件的可执行程序以及我们的渲染器在此https URL可用。为了展示我们数据集的可用性和独特性，我们展示了稀疏和密集SLAM算法的基准测试结果。
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.