Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Warping
Bilateral Filtering for Gray and Color Images
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Automatic thumbnail cropping and its effectiveness
Proceedings of the 16th annual ACM symposium on User interface software and technology
Seam carving for content-aware image resizing
ACM SIGGRAPH 2007 papers
Multi-operator media retargeting
ACM SIGGRAPH 2009 papers
Energy-based image deformation
SGP '09 Proceedings of the Symposium on Geometry Processing
NPAR '12 Proceedings of the Symposium on Non-Photorealistic Animation and Rendering
NPAR '12 Proceedings of the Symposium on Non-Photorealistic Animation and Rendering
Parameterization-Aware MIP-Mapping
Computer Graphics Forum
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
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.