전자통신동향분석 (Electronics and Telecommunications Trends)

한국전자통신연구원 (Electronics and Telecommunications Research Institute)
권호 표지
DOI QR코드

DOI QR Code

딥러닝기반 입체 영상의 획득 및 처리 기술 동향

Recent Technologies for the Acquisition and Processing of 3D Images Based on Deep Learning

  • 발행 : 2020.10.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In 3D computer graphics, a depth map is an image that provides information related to the distance from the viewpoint to the subject's surface. Stereo sensors, depth cameras, and imaging systems using an active illumination system and a time-resolved detector can perform accurate depth measurements with their own light sources. The 3D image information obtained through the depth map is useful in 3D modeling, autonomous vehicle navigation, object recognition and remote gesture detection, resolution-enhanced medical images, aviation and defense technology, and robotics. In addition, the depth map information is important data used for extracting and restoring multi-view images, and extracting phase information required for digital hologram synthesis. This study is oriented toward a recent research trend in deep learning-based 3D data analysis methods and depth map information extraction technology using a convolutional neural network. Further, the study focuses on 3D image processing technology related to digital hologram and multi-view image extraction/reconstruction, which are becoming more popular as the computing power of hardware rapidly increases.

키워드

참고문헌

  1. S. Im et al., "Deep Depth from Uncalibrated Small Motion Clip," IEEE Trans. Pattern Anal. Mach. Intell., 2019, pp. 1-14.
  2. S. Im et al., "DPSNet: End-to-end Deep Plane Sweep Stereo," ICLR2019, 2019.
  3. A. W. Bergman, D. B. Lindell, and G. Wetzstein "Deep Adaptive LiDAR: End-to-end Optimization of Sampling and Depth Completion at Low Sampling Rates," IEEE Int. Conf. Comput. Photography, 2020, pp. 1-11.
  4. I. Alhashim and P. Wonka, "High Quality Monocular Depth Estimation via Transfer Learning," arXiv preprint arXiv:1812.11941, 2018.
  5. M. Yoon, H. Kim, and H.S. Yeo, "Deep Depth Extraction of Multi-view Images for Holographic 3D Content," 2020 International Meeting on Information Display (IMID), 2020.
  6. Z. Hao et al., "Detail preserving depth estimation from a single image using attention guided networks," Int. Conf. 3D Vision (3DV), 2018, pp. 304-313.
  7. W. Zhou, X. Li, and D. Reynolds, "Guided deep network for depth map super-resolution: How much can color help?" IEEE Int. Conf. on Acoustics, Speech Signal Process., 2017, pp. 1457-1461.
  8. 윤민성, "디지털홀로그래피콘텐츠기술," 전자통신동향분석, 32권 5호, 2017, pp. 49-64. https://doi.org/10.22648/ETRI.2017.J.320506
  9. 윤민성, 회절광학 및 홀로그래피, BOOKK, 2019.
  10. 윤민성, 디지털 홀로그램과 디스플레이(개정판), BOOKK, 2020.
  11. R. Horisaki, R. Takagi, and J. Tanida, "Deep-learning-generated holography," Appl. Opt., vol. 57, no. 14, 2018, pp. 3859-3863. https://doi.org/10.1364/AO.57.003859
  12. Z. Ren, Z. Xu, and E. Lam, "End-to-end deep learning framework for digital holographic reconstruction," Advanced Photonics, vol. 1, no. 1, 2018, p. 016004.
  13. Z. Ren, H. So and E. Lam, "Fringe Pattern Improvement and Super-Resolution Using Deep Learning in Digital Holography," IEEE Trans. Ind. Inf., vol. 15, no. 11, 2019, pp. 6179-6186. https://doi.org/10.1109/TII.2019.2913853
  14. Y. Rivenson and A. Ozcan, "Deep learning microscopy," Optica, Vol. 4, no. 11, 2017, pp. 1437-1443. https://doi.org/10.1364/OPTICA.4.001437
  15. L. Xiao et al., "DeepFocus: learned image synthesis for computational display," ACM Trans. Graph., vol. 37, no. 6, 2018, Article no. 200.