%0 Generic %1 dai2017scannet %A Dai, Angela %A Chang, Angel X. %A Savva, Manolis %A Halber, Maciej %A Funkhouser, Thomas %A Nießner, Matthias %D 2017 %K 2017 3D arxiv computer-vision cvpr dataset paper reconstruction segmentation semantic %R 10.1109/CVPR.2017.261 %T ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes %U http://arxiv.org/abs/1702.04405 %X 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.

@misc{dai2017scannet, abstract = {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.}, added-at = {2018-08-02T13:08:05.000+0200}, author = {Dai, Angela and Chang, Angel X. and Savva, Manolis and Halber, Maciej and Funkhouser, Thomas and Nießner, Matthias}, biburl = {https://www.bibsonomy.org/bibtex/29195fb474cf50ec367ae3b7c4ecf3108/analyst}, description = {[1702.04405] ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes}, doi = {10.1109/CVPR.2017.261}, interhash = {87f9761c1fe03a0e4fd5972ecb3387ed}, intrahash = {9195fb474cf50ec367ae3b7c4ecf3108}, keywords = {2017 3D arxiv computer-vision cvpr dataset paper reconstruction segmentation semantic}, note = {cite arxiv:1702.04405}, timestamp = {2018-08-02T13:15:35.000+0200}, title = {ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes}, url = {http://arxiv.org/abs/1702.04405}, year = 2017 }