swMATH ID: 36659
Software Authors: Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner
Description: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available – current datasets cover a small range of scene views and have limited semantic annotations. To address this issue, we introduce ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations. To collect this data, we designed an easy-to-use and scalable RGB-D capture system that includes automated surface reconstruction and crowdsourced semantic annotation. We show that using this data helps achieve state-of-the-art performance on several 3D scene understanding tasks, including 3D object classification, semantic voxel labeling, and CAD model retrieval. The dataset is freely available at http://www.scan-net.org
Homepage: http://www.scan-net.org
Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV
Related Software: PointNet; ImageNet; SceneNN; DeepLab; Cityscapes; TensorFlow; AlexNet; MS-COCO; PointSIFT; VoxNet; OctNet; SYNTHIA Dataset; RGCNN; ScanComplete; PASCAL VOC; ShapeNet; NYU Depth; Faster R-CNN; MinkowskiEngine; KPConv
Cited in: 4 Publications

Citations by Year