DOI QR코드

DOI QR Code

Recent R&D Trends for 3D Deep Learning

3D 딥러닝 기술 동향

  • Published : 2018.10.01

Abstract

Studies on artificial intelligence have been developed for the past couple of decades. After a few periods of prosperity and recession, a new machine learning method, so-called Deep Learning, has been introduced. This is the result of high-quality big- data, an increase in computing power, and the development of new algorithms. The main targets for deep learning are 1D audio and 2D images. The application domain is being extended from a discriminative model, such as classification/segmentation, to a generative model. Currently, deep learning is used for processing 3D data. However, unlike 2D, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become more popular owing to advances in 3D vision technology, the generation/acquisition of 3D data remains a very difficult problem. Moreover, it is not easy to directly apply an existing network model, such as a convolution network, owing to the variety of 3D data representations. In this paper, we summarize the 3D deep learning technology that have started to be developed within the last 2 years.

Keywords

Acknowledgement

Grant : 게임 및 애니메이션을 위한 인공 지능 기반의 3D 캐릭터 생성 기술 개발

Supported by : 한국콘텐츠진흥원

References

  1. S. Khan and S.P.Yong, "A Comparison of Deep Learning and Hand Crafted Features in Medical Image Modality Classification," Int. Conf. Comput. Inform. Sci., Kuala Lumpur, Malaysia, Aug. 15-17, 2016, pp. 633-638.
  2. T . Kim, "CNN, Convolution Neural Network 요약," Tawan.Kim Blog, Jan. 4, 2018. Available: http://taewan.-kim/post/cnn/
  3. 강대기, "딥러닝 기반 기계학습 기술 동향," 주간기술동향, 2016, pp. 12-24.
  4. I. J. Goodfellow et al., "Generative Adversarial Nets." Adv. Neural Inform. Process. Syst., Montreal, Canada, Dec. 8-13, 2014, pp. 1-9.
  5. A Tutorial on 3D Deep Learning, 2017. Available: http://3ddl.stanford.edu/
  6. Z. Lun, E. Kalogerakis, R. Wang, and A. Sheffer, "Functionality Preserving Shape Style Transfer," ACM Trans, Graphics (TOG), vol. 35, no. 6, Nov. 2016, pp. 209:1-209:14.
  7. Y. Zheng, D. Cohen-Or, and H.J. Mitra, "Smart Variations: Functional Substructures for Part Compatibility," Comput. Graphics Forum, vol. 32, no. 2, May, 2013, pp. 195-204.
  8. E. Kalogerakis et al., "A Probabilistic Model for Component-Based Shape Synthesis," ACM Trans. Graphics, vol. 31, no. 4, July 2012, pp. 55:1-55:11.
  9. A. Kar, S. Tulsiani, J. Carreira, and J. Malik, "Category-Specific Object Reconstruction from a Single Image," IEEE Conf. comput. Vis. Pattern, Recogn. (CVPR), Boston, MA, USA, June 7-12, 2015, pp. 1966-1974.
  10. J. Rock, T. Gupta, J. Thorsen, J. Gwak, D. Shin, and D. Hoiem, "Completing 3D Object Shape from one Depth Image," IEEE Conf. comput. Vis. Pattern, Recogn. (CVPR), Boston, MA, USA, June 7-12, 2015, pp. 2484-2493.
  11. Z. Lun, M. Gadelha, E. Kalogerakis, S. Maji, and R. Wang, "3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks," Sept. 2017, arXiv: 1707.06375.
  12. E. Dibra, H. Jain, C. Oztireli, R. Ziegler, and M. Gross, "HSNets: Estimating Human Body Shape from Silhouettes with Convolutional Neural Networks," Int. Conf. 3D Vision (3DV), Stanford, CA, USA, Oct. 25-28, 2016, pp. 108-117.
  13. H. Fan, H. Su, and L. Guibas, "A Point Set Generation Network for 3D Object Reconstruction from a Single Image," Dec. 2016, arXiv: 1612.00603.
  14. J. Wu et al., "Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling," Proc. Int. Conf. Neural Inform. Process. Syst., Barcelona, Spain, Dec. 5-10, 2016, pp. 82-90.
  15. A.S. Jackson, A. Bulat, V. Argyriou, and G. Tzimiropoulos, "3D Face Reconstruction demo," Available: http://cvldemos.cs.nott.ac.uk/vrn/
  16. H. Su, S. Maji, E. Kalogerakis, and E. Learned-Miller, "Multi-view Convolutional Neural Networks for 3D Shape Recognition," Sept. 2015, arXiv: 1505.00880.
  17. Kalogerakis, Averkiou, Maji, Chaudhuri, "3D Shape Segmentation with Projective Convolutional Networks," IEEE Conf. Comput. Vis. Pattern, Recogn. (CVPR), Honolulu, HI, USA, July 21-26, 2017, pp. 6630-6639.
  18. C.R. Qi et al., "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation," Apr. 2017, arXiv: 1612.00593.
  19. Geometric Deep Learning, Available: http://geometricdeeplearning.com/