Nicolas Weber
Michael Waechter
Michael Goesele
Abstract
Image downscaling is arguably the most frequently used image processing tool. We present an algorithm based on convolutional filters where input pixels contribute more to the output image the more their color deviates from their local neighborhood, which preserves visually important details. In a user study we verify that users prefer our results over related work. Our efficient GPU implementation works in real-time when downscaling images from 24 M to 70 k pixels. Further, we demonstrate empirically that our method can be successfully applied to videos.
Supplemental Material
Available for Download
Supplemental file.
- Beghdadi, A., Larabi, M.-C., Bouzerdoum, A., and Iftekharuddin, K. 2013. A survey of perceptual image processing methods. Signal Processing: Image Communication 28, 8.Google Scholar
Cross Ref
- Duchon, C. E. 1979. Lanczos filtering in one and two dimensions. Journal of Applied Meteorology 18, 8.Google ScholarCross Ref
- Eisemann, E., and Durand, F. 2004. Flash photography enhancement via intrinsic relighting. In SIGGRAPH. Google ScholarDigital Library
- Kopf, J., Cohen, M., Lischinski, D., and Uyttendaele, M. 2007. Joint bilateral upsampling. In SIGGRAPH. Google ScholarDigital Library
- Kopf, J., Shamir, A., and Peers, P. 2013. Content-adaptive image downscaling. In SIGGRAPH Asia. Google ScholarDigital Library
- National Aeronautics and Space Administration, 2016. NASA image gallery. nasa.gov/multimedia/imagegallery.Google Scholar
- Nehab, D., and Hoppe, H. 2011. Generalized sampling in computer graphics. Tech. Rep. MSR-TR-2011-16.Google Scholar
- Öztireli, A. C., and Gross, M. 2015. Perceptually based downscaling of images. In SIGGRAPH. Google ScholarDigital Library
- Petschnigg, G., Agrawala, M., Hoppe, H., Szeliski, R., Cohen, M., and Toyama, K. 2004. Digital photography with flash and no-flash image pairs. In SIGGRAPH. Google ScholarDigital Library
- Samadani, R., Mauer, T. A., Berfanger, D. M., and Clark, J. H. 2010. Image thumbnails that represent blur and noise. Transactions on Image Processing 19, 2. Google ScholarDigital Library
- Schall, S., and Schmid, L., 2015. Fuerteventura 4K - A Time-lapse Adventure. youtu.be/40s_HSZkt3U.Google Scholar
- Shannon, C. E. 1949. Communication in the presence of noise. Proc. IRE 37.Google ScholarCross Ref
- Thomee, B., Shamma, D. A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., and Li, L.-J. 2016. YFCC100M: The new data in multimedia research. Communications of the ACM 59, 2. Google ScholarDigital Library
- Trentacoste, M., Mantiuk, R., and Heidrich, W. 2011. Blur-aware image downsampling. Comput. Graph. Forum 30, 2.Google ScholarCross Ref
- Triggs, B. 2001. Empirical filter estimation for subpixel interpolation and matching. In ICCV.Google Scholar
Index Terms
- Rapid, detail-preserving image downscaling
Recommendations
A New Image Downscaling Algorithm based on a Circular Area Pixel Model
ICVIP '22: Proceedings of the 2022 6th International Conference on Video and Image ProcessingImage downscaling is a fundamental task for most image and video applications, and many research works have been proposed. Although most of them try to get a scaled image of higher quality and to reduce the processing time further, to develop more and ...
Spectral remapping for image downscaling
We present an image downscaling technique capable of appropriately representing high-frequency structured patterns. Our method breaks conventional wisdom in sampling theory---instead of discarding high-frequency information to avoid aliasing, it ...
Image downscaling via co-occurrence learning
AbstractImage downscaling is one of the widely used operations in image processing and computer graphics. It was recently demonstrated in the literature that kernel-based convolutional filters could be modified to develop efficient image ...
Comments