Journal of the Korea Computer Graphics Society (한국컴퓨터그래픽스학회논문지)

Korea Computer Graphics Society (한국컴퓨터그래픽스학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-Based Lighting Estimation for Indoor and Outdoor

딥러닝기반 실내와 실외 환경에서의 광원 추출

  • 이지원 (카이스트 비주얼미디어연구실) ;
  • 서광균 (카이스트 비주얼미디어연구실) ;
  • 이하늬 (카이스트 비주얼미디어연구실) ;
  • 유정은 (카이스트 비주얼미디어연구실) ;
  • 노준용 (카이스트 비주얼미디어연구실)
  • Received : 2021.06.02
  • Accepted : 2021.06.25
  • Published : 2021.07.23
Download PDF
⟨ Previous Next ⟩

Abstract

We propose a deep learning-based method that can estimate an appropriate lighting of both indoor and outdoor images. The method consists of two networks: Crop-to-PanoLDR network and LDR-to-HDR network. The Crop-to-PanoLDR network predicts a low dynamic range (LDR) environment map from a single partially observed normal field of view image, and the LDR-to-HDR network transforms the predicted LDR image into a high dynamic range (HDR) environment map which includes the high intensity light information. The HDR environment map generated through this process is applied when rendering virtual objects in the given image. The direction of the estimated light along with ambient light illuminating the virtual object is examined to verify the effectiveness of the proposed method. For this, the results from our method are compared with those from the methods that consider either indoor images or outdoor images only. In addition, the effect of the loss function, which plays the role of classifying images into indoor or outdoor was tested and verified. Finally, a user test was conducted to compare the quality of the environment map created in this study with those created by existing research.

본 연구에서는 딥러닝을 기반으로 하여 실내와 실외 이미지 모두에서 알맞은 광원을 추출하는 방법론을 소개한다. 네트워크는 단일 LDR 이미지로부터 실내 혹은 실외 배경에 맞는 광원을 low dynamic range (LDR) 환경 맵으로 추출하는 Crop-to-PanoLDR 네트워크와 추출된 LDR 환경 맵을 빛의 정보를 담은 high dynamic range (HDR) 환경 맵으로 생성하는 LDR-to-HDR 네트워크 두 단계로 구성된다. 이와 같은 과정을 통해 최종적으로 생성된 HDR 환경 맵은 주어진 이미지에서 가상 객체를 렌더링할 때 적용되어 가상 객체를 조명하는 빛의 방향과 주변광 등을 확인함으로써 자연스러운 렌더링을 가능하게 하는지 검증한다. 본 연구에서 제안한 방법론의 우수성은 실내를 배경으로 한 이미지로만 구성한 데이터로 학습한 결과와 실외를 배경으로 한 이미지로만 학습한 결과 등과 비교하여 검증하였다. 또한, 실내와 실외를 구분하는 역할을 수행하는 손실 함수가 학습 결과에 미치는 영향을 실험, 검증하였다. 최종적으로 본 연구에서 생성된 환경 맵을 기존의 연구 결과와 비교 실험하는 사용자 테스트를 진행하였고 더 좋은 결과를 확인할 수 있었다.

Keywords

Acknowledgement

이 논문은 2021년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임 (No.2020-0-00450, AR 실감 콘텐츠 제작을 위한 심층학습 기반 단일 이미지의 입체적 움직임 자동 생성 및 대화형 증강 기술 개발)

References

  1. P. Debevec, "Rendering synthetic objects into real scenes: Bridging traditional and image-based graphics with global illumination and high dynamic range photography," 1998.
  2. M.-A. Gardner, K. Sunkavalli, E. Yumer, X. Shen, E. Gambaretto, C. Gagne, and J.-F. Lalonde, "Learning to predict indoor illumination from a single image," 2017.
  3. M.-A. Gardner, Y. Hold-Geoffroy, K. Sunkavalli, C. Gagne, and J.-F. Lalonde, "Deep parametric indoor lighting estimation," 2019.
  4. M. Garon, K. Sunkavalli, S. Hadap, N. Carr, and J.-F. Lalonde, "Fast spatially-varying indoor lighting estimation," 2019.
  5. Y. Hold-Geoffroy, K. Sunkavalli, S. Hadap, E. Gambaretto, and J. Lalonde, "Deep outdoor illumination estimation," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2373-2382.
  6. Y. Hold-Geoffroy, A. Athawale, and J.-F. Lalonde, "Deep sky modeling for single image outdoor lighting estimation," 2019.
  7. J. Zhang, K. Sunkavalli, Y. Hold-Geoffroy, S. Hadap, J. Eisenmann, and J.-F. Lalonde, "All-weather deep outdoor lighting estimation," 2019.
  8. P. Debevec, "Image-based lighting," IEEE Computer Graphics and Applications, vol. 22, no. 2, pp. 26-34, 2002. https://doi.org/10.1109/38.988744
  9. P. Debevec, P. Graham, J. Busch, and M. Bolas, "A single-shot light probe," in ACM SIGGRAPH 2012 Talks, ser. SIGGRAPH '12. New York, NY, USA: Association for Computing Machinery, 2012. [Online]. Available: https://doi.org/10.1145/2343045.2343058
  10. S. Song and T. Funkhouser, "Neural illumination: Lighting prediction for indoor environments," 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6911-6919, 2019.
  11. F. Banterle, P. Ledda, K. Debattista, and A. Chalmers, "Inverse tone mapping," in Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia, ser. GRAPHITE '06. New York, NY, USA: Association for Computing Machinery, 2006, p. 349-356. [Online]. Available: https://doi.org/10.1145/1174429.1174489
  12. P. E. Debevec and J. Malik, "Recovering high dynamic range radiance maps from photographs," in Proceedings of the 24th Annual Conference on Computer Graphics and Interactive Techniques, ser. SIGGRAPH '97. USA: ACM Press/Addison-Wesley Publishing Co., 1997, p. 369-378. [Online]. Available: https://doi.org/10.1145/258734.258884
  13. M. Fan, D.-H. Lee, S. Kim, and S.-J. Ko, "An optimization framework for inverse tone mapping using a single low dynamic range image," Signal Process. Image Commun., vol. 78, pp. 274-283, 2019. https://doi.org/10.1016/j.image.2019.07.009
  14. P. Kuo, C. Tang, and S. Chien, "Content-adaptive inverse tone mapping," in 2012 Visual Communications and Image Processing, 2012, pp. 1-6.
  15. X. Li and Y. Huo, "Hdr image reconstruction using locally weighted linear regression," in 2018 IEEE International Conference on Multimedia Expo Workshops (ICMEW), 2018, pp. 1-6.
  16. A. G. Rempel, M. Trentacoste, H. Seetzen, H. D. Young, W. Heidrich, L. Whitehead, and G. Ward, "Ldr2hdr: On-thefly reverse tone mapping of legacy video and photographs," ACM Trans. Graph., vol. 26, no. 3, p. 39-es, July 2007. [Online]. Available: https://doi.org/10.1145/1276377.1276426
  17. S. Lee, G. H. An, and S.-J. Kang, "Deep recursive hdri: Inverse tone mapping using generative adversarial networks," in Proceedings of the European Conference on Computer Vision (ECCV), September 2018.
  18. Y. Kinoshita and H. Kiya, "itm-net: Deep inverse tone mapping using novel loss function considering tone mapping operator," IEEE Access, vol. 7, pp. 73 555-73 563, 2019. https://doi.org/10.1109/ACCESS.2019.2919296
  19. Y.-L. Liu, W.-S. Lai, Y.-S. Chen, Y.-L. Kao, M.-H. Yang, Y.- Y. Chuang, and J.-B. Huang, "Single-image hdr reconstruction by learning to reverse the camera pipeline," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
  20. J. Zhang and J.-F. Lalonde, "Learning high dynamic range from outdoor panoramas," 2017.
  21. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," 2015.
  22. J. Xiao, K. A. Ehinger, A. Oliva, and A. Torralba, "Recognizing scene viewpoint using panoramic place representation," in 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 2695-2702.
  23. T. Rhee, L. Petikam, B. Allen, and A. Chalmers, "Mr360: Mixed reality rendering for 360° panoramic videos," IEEE Transactions on Visualization and Computer Graphics, vol. 23, no. 4, pp. 1379-1388, 2017. https://doi.org/10.1109/TVCG.2017.2657178
  24. J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, "Unpaired imageto-image translation using cycle-consistent adversarial networks," 2020.
  25. D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," 2017.
  26. S. Ning, H. Xu, L. Song, R. Xie, and W. Zhang, "Learning an inverse tone mapping network with a generative adversarial regularizer," in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, pp. 1383-1387.