Non-Photorealistic Rendering Using CUDA-Based Image Segmentation

CUDA 기반 영상 분할을 사용한 비사실적 렌더링

Yoon, Hyun-Cheol;Park, Jong-Seung

  • Received : 2015.05.11
  • Accepted : 2015.06.27
  • Published : 2015.11.30


When rendering both three-dimensional objects and photo images together, the non-photorealistic rendering results are in visual discord since the two contents have their own independent color distributions. This paper proposes a non-photorealistic rendering technique which renders both three-dimensional objects and photo images such as cartoons and sketches. The proposed technique computes the color distribution property of the photo images and reduces the number of colors of both photo images and 3D objects. NPR is performed based on the reduced colormaps and edge features. To enhance the natural scene presentation, the image region segmentation process is preferred when extracting and applying colormaps. However, the image segmentation technique needs a lot of computational operations. It takes a long time for non-photorealistic rendering for large size frames. To speed up the time-consuming segmentation procedure, we use GPGPU for the parallel computing using the GPU. As a result, we significantly improve the execution speed of the algorithm.


Non-Photorealistic Rendering;CUDA;Image;Segmentation;Colormap


  1. H. Lee and J. Choi, "Cartoon rendering techniques for real-time applications," Korea Multimedia Society, Vol.9, No.3-4, pp.54-64, 2005.
  2. P. Decaudin, "Cartoon-Looking Rendering of 3D-Scenes," Research Report INRIA #2919, Jun., 1996.
  3. J. Shi and J. Malik, "Normalized cuts and image segmentation," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.22, No.8, pp.888-905. 2000.
  4. Y. J. Zhang, "A survey on evaluation methods for image segmentation," Pattern recognition, Vol.29, No.8, pp.1335- 1346. 1996.
  5. T. Son and K. Park, "Various line stylization of realtime video using the Image Difference and CUDA," HCI'2012 Conference, pp.382-385, 2012.
  6. S. Jang and H. Hong, "Color-based Stippling for Non- Photorealistic Rendering," Journal of KIISE: Computer Systems and Theory, Vol.33, No.2, pp.128-136, 2006.
  7. H. Joo, "A Study on 3D Cartoon Animation for Production in Non-Photo Realistic Rendering Technique," Journal of The Korean Society for Computer Game, Vol.26, No.4, pp. 179-185, 2013.
  8. H. Lee, S. Seo, and K. Yoon, "A Study on Saliency-based Stroke LOD for Painterly Rendering," Journal of KIISE: Computer Systems and Theory, Vol.36, No.3, pp.199-209, 2009.
  9. H. Jang, J. Jeon, and Y. Choy, "Processing Methods for Ink-and-Wash Painting in Mobile Contents," Journal of the Korea Contents Association, Vol.11, No.3, pp.137-146, 2011.
  10. S. Choi, "A Simple and Fast Algorithm for Real-time Pencil Strokes," Journal of KIISE: Computer Systems and Theory, Vol.33, No.6, pp.344-353, 2006.
  11. B. Gooch, and A. Gooch, "Non-photorealistic rendering," AK Peters, Ltd., 2001.
  12. A. Hertzmann, "Introduction to 3D non-photorealistic rendering: Silhouettes and outlines," SIGGRAPH'99 Course, pp.21-26, 1999.
  13. H. P. Narkhede, "Review of Image Segmentation Techniques," International Journal of Science and Modern Engineering, pp.2319-6386. 2013.
  14. P. F. Felzenszwalb and D. P. Huttenlocher, "Efficient graph-based image segmentation," International Journal of Computer Vision, Vol.59, No.2, pp.167-181, 2004.
  15. Y. Y. Boykov and M. P. Jolly, "Interactive graph cuts for optimal boundary & region segmentation of objects in ND images," in Proceedings of IEEE ICCV'2001, Vol.1, pp.105-112, 2001.
  16. B. Fulkerson and S. Stefano, "Really quick shift: Image segmentation on a GPU," Trends and Topics in Computer Vision, Springer Berlin Heidelberg, pp.350-358, 2012.
  17. I. Buck, "GPU computing with NVIDIA CUDA," SIGGRAPH'2007 Course, 2007.
  18. S. Che, M. Boyer, J. Meng, D. Tarjan, J. W. Sheaffer, and K. Skadron, "A performance study of general-purpose applications on graphics processors using CUDA," Journal of parallel and distributed computing, Vol.68, No.10, pp. 1370-1380. 2008.


Supported by : 인천대학교