Seite - 113 - in Joint Austrian Computer Vision and Robotics Workshop 2020

ACKNOWLEDGMENT Thisworkhasbeensupportedby theAustrianRe- searchPromotionAgency in theprogramProduction of the Future funded project MMAssist II (FFG No. 858623), the Austrian Ministry for Transport, Inno- vationandTechnology(bmvit) and theAustrianSci- ence Foundation (FWF) under grant agreement No. I3969-N30 (InDex). References [1] A. Dosovitskiy, P. Fischer, E. Ilg, P. Hausser, C. Hazirbas, V. Golkov, P. Van Der Smagt, D. Cre- mers, and T. Brox. Flownet: Learning optical flow with convolutional networks. In Proceedings of the IEEE international conference on computer vision, pages2758–2766,2015. [2] K.He,G.Gkioxari,P.Dolla´r,andR.Girshick. Mask r-cnn. InProceedingsof theIEEEinternationalcon- ferenceoncomputervision,pages2961–2969,2017. [3] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pages770–778,2016. [4] S. Hinterstoisser, V. Lepetit, S. Ilic, S. Holzer, G. Bradski, K. Konolige, and N. Navab. Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In Proceedings of Asian conference on computer vi- sion, pages548–562,2012. [5] T. Hodan, F. Michel, E. Brachmann, W. Kehl, A. GlentBuch, D. Kraft, B. Drost, J. Vidal, S. Ihrke, X.Zabulis,etal. Bop: Benchmarkfor6dobjectpose estimation. In Proceedings of the European Con- ference on Computer Vision (ECCV), pages 19–34, 2018. [6] M. Jaderberg, K. Simonyan, A. Zisserman, et al. Spatial transformernetworks. InAdvances inneural information processing systems, pages 2017–2025, 2015. [7] W. Kehl, F. Manhardt, F. Tombari, S. Ilic, and N. Navab. SSD-6D: making rgb-based 3d detec- tion and 6d pose estimation great again. CoRR, abs/1711.10006,2017. [8] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Im- agenet classification with deep convolutional neural networks. In Advances in neural information pro- cessingsystems, pages 1097–1105,2012. [9] K. Lenc and A. Vedaldi. Understanding image rep- resentations by measuring their equivariance and equivalence. InProceedingsof the IEEEconference on computer vision and pattern recognition, pages 991–999,2015. [10] Y.Li,G.Wang,X.Ji,Y.Xiang,andD.Fox.Deepim: Deep iterative matching for 6d pose estimation. In Proceedings of the European Conference on Com- puterVision (ECCV), pages 683–698,2018. [11] C.-H. Lin, E. Yumer, O. Wang, E. Shechtman, and S. Lucey. St-gan: Spatial transformer generative adversarial networks for image compositing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 9455–9464, 2018. [12] F. Manhardt, W. Kehl, N. Navab, and F. Tombari. Deepmodel-based6dposerefinementinrgb. InPro- ceedings of the European Conference on Computer Vision (ECCV), pages800–815,2018. [13] M. Oberweger, M. Rad, and V. Lepetit. Making deep heatmaps robust to partial occlusions for 3d object pose estimation. In Proceedings of the Eu- ropean Conference on Computer Vision (ECCV), pages 119–134,2018. [14] C. R. Qi, H. Su, K. Mo, and L. J. Guibas. Point- net: Deep learningonpoint sets for3dclassification and segmentation. In Proceedings of the IEEE con- ference on computer vision and pattern recognition, pages 652–660,2017. [15] C.R.Qi,L.Yi,H.Su,andL.J.Guibas. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In Advances in neural information processing systems, pages 5099–5108,2017. [16] M. Rad and V. Lepetit. Bb8: A scalable, accurate, robust topartial occlusionmethod forpredicting the 3dposesofchallengingobjectswithoutusingdepth. In Proceedings of the IEEE International Confer- ence onComputerVision, pages3828–3836,2017. [17] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al. Imagenet large scale visual recognition challenge. International Journal ofComputer Vision, 115:211–252, 2015. [18] M. Sundermeyer, Z.-C. Marton, M. Durner, M. Brucker, and R. Triebel. Implicit 3d orientation learning for6dobjectdetection from rgb images. In Proceedings of the European Conference on Com- puterVision (ECCV), pages 699–715,2018. [19] D. E. Worrall, S. J. Garbin, D. Turmukhambetov, and G. J. Brostow. Interpretable transformations with encoder-decoder networks. In Proceedings of the IEEEInternationalConferenceonComputerVi- sion, pages5726–5735,2017. [20] Y. Xiang, T. Schmidt, V. Narayanan, and D. Fox. Posecnn: Aconvolutionalneuralnetwork for6dob- jectposeestimation inclutteredscenes. 2018. [21] S.Zakharov, I.Shugurov,andS. Ilic. Dpod: 6dpose object detector and refiner. In Proceedings of the IEEEInternationalConferenceonComputerVision, pages 1941–1950,2019. 113