A study of the effect of noise and occlusion on the accuracy of convolutional neural networks applied to 3D object recognition
Tài liệu tham khảo
Gschwandtner, 2011, Blensor: blender sensor simulation toolbox, 199
Höft, 2014, Fast semantic segmentation of rgb-d scenes with gpu-accelerated deep neural networks, 80
Lai, 2011, A large-scale hierarchical multi-view rgb-d object dataset, 1817
Li, 2014, Shrec’14 track: extended large scale sketch-based 3d shape retrieval, 121
Maturana, 2015
Maturana, 2015
Pan, 2010, A survey on transfer learning, Knowl. Data Eng. IEEE Trans., 22, 1345, 10.1109/TKDE.2009.191
Rusu, 2011, 3d is here: Point cloud library (pcl), 1
Schwarz, 2015, Rgb-d object recognition and pose estimation based on pre-trained convolutional neural network features, 1329
Sedaghat, N., Zolfaghari, M., Brox, T., 2016. Orientation-boosted voxel nets for 3d object recognition. arXiv preprint arXiv:1604.03351.
Shi, 2015, Deeppano: deep panoramic representation for 3-d shape recognition, Sig. Process. Lett. IEEE, 22, 2339, 10.1109/LSP.2015.2480802
Socher, 2012, Convolutional-recursive deep learning for 3d object classification, 665
Song, 2015, Deep sliding shapes for amodal 3d object detection in RGB-D images, CoRR, abs/1511.02300
Wang, 2015, Convolutional neural network for 3d object recognition based on rgb-d dataset, 34
Wu, 2015, 3d shapenets: a deep representation for volumetric shape modeling, 1, 3