“Content-adaptive image downscaling” by Kopf, Shamir and Peers
Conference:
Type(s):
Title:
- Content-adaptive image downscaling
Session/Category Title: Image Ops
Presenter(s)/Author(s):
Abstract:
This paper introduces a novel content-adaptive image downscaling method. The key idea is to optimize the shape and locations of the downsampling kernels to better align with local image features. Our content-adaptive kernels are formed as a bilateral combination of two Gaussian kernels defined over space and color, respectively. This yields a continuum ranging from smoothing to edge/detail preserving kernels driven by image content. We optimize these kernels to represent the input image well, by finding an output image from which the input can be well reconstructed. This is technically realized as an iterative maximum-likelihood optimization using a constrained variation of the Expectation-Maximization algorithm. In comparison to previous downscaling algorithms, our results remain crisper without suffering from ringing artifacts. Besides natural images, our algorithm is also effective for creating pixel art images from vector graphics inputs, due to its ability to keep linear features sharp and connected.
References:
1. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., and Süsstrunk, S. 2012. Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34, 11, 2274–2282.
2. Avidan, S., and Shamir, A. Seam carving for content-aware image resizing. ACM Transactions on Graphics, (Proc. SIGGRAPH 2007) 26, 3, article no. 10.
3. Comaniciu, D., Meer, P., and Member, S. 2002. Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 603–619.
4. Gerstner, T., DeCarlo, D., Alexa, M., Finkelstein, A., Gingold, Y., and Nealen, A. 2012. Pixelated image abstraction. Proceedings of the International Symposium on Non-Photorealistic Animation and Rendering (NPAR), 29–36.
5. Hastie, T., Tibshirani, R., Friedman, J., and Franklin, J. 2005. The elements of statistical learning: data mining, inference and prediction. The Mathematical Intelligencer 27, 2, 83–85.
6. Inglis, T. C., and Kaplan, C. S. 2012. Pixelating vector line art. Proceedings of the Symposium on Non-Photorealistic Animation and Rendering, 21–28.
7. Karni, Z., Freedman, D., and Gotsman, C. 2009. Energy-based image deformation. Proceedings of the Symposium on Geometry Processing (SGP 2009), 1257–1268.
8. Liu, T., Sun, J., Zheng, N.-N., Tang, X., and Shum, H.-Y. 2007. Learning to detect a salient object. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2007), 1–8.
9. Manson, J., and Schaefer, S. 2012. Parameterization-aware mip-mapping. Computer Graphics Forum (Proc. Eurographics Symposium on Rendering) 31, 4, 1455–1463.
10. Nehab, D., and Hoppe, H. 2011. Generalized sampling for computer graphics. Tech. rep., feb.
11. Rubinstein, M., Shamir, A., and Avidan, S. 2009. Multi-operator media retargeting. ACM Transactions on Graphics (Proceedings SIGGRAPH 2009) 28, 3, 1–11.
12. Samadani, R., Lim, S. H., and Tretter, D. 2007. Representative image thumbnails for good browsing. Proceedings of the International Conference on Image Processing (ICIP 2007), 193–196.
13. Shannon, C. E. 1949. Communication in the presence of noise. Proceedings of the Institute of Radio Engineers 37, 1, 10–21.
14. Suh, B., Ling, H., Bederson, B. B., and Jacobs, D. W. 2003. Automatic thumbnail cropping and its effectiveness. Proceedings of the 16th annual ACM symposium on User interface software and technology, 95–104.
15. Tomasi, C., and Manduchi, R. 1998. Bilateral filtering for gray and color images. Proceedings of IEEE International Conference on Computer Vision (ICCV ’98), 836–846.
16. Trentacoste, M., Mantiuk, R., and Heidrich, W. 2011. Blur-aware image downsizing. Computer Graphics Forum (Proc. Eurographics 2011) 30, 2, 573–582.
17. Triggs, B. 2001. Empirical filter estimation for subpixel interpolation and matching. Proceedings of IEEE International Conference on Computer Vision (ICCV 2001) 2, 550–557.
18. Wolberg, G. 1990. Digital Image Warping. IEEE Computer Society Press, Los Alamitos, CA, USA.
19. Wolf, L., Guttmann, M., and Cohen-Or, D. 2007. Non-homogeneous content-driven video-retargeting. Proceedings of IEEE International Conference on Computer Vision (ICCV 2007), 1–6.
