Abstract not found

Abstract. In this paper, we propose a novel type of explicit image filter- guided filter. Derived from a local linear model, the guided filter generates the filtering output by considering the content of a guidance image, which can be the input image itself or another different image. The guided filter can perform as an edge-preserving smoothing operator like the popular bilateral filter [1], but has better behavior near the edges. It also has a theoretical connection with the matting Laplacian matrix [2], so is a more generic concept than a smoothing operator and can better utilize the structures in the guidance image. Moreover, the guidedfilterhasafastandnon-approximatelinear-time algorithm, whose computational complexity is independent of the filtering kernel size. We demonstrate that the guided filter is both effective and efficient in a great variety of computer vision and computer graphics applications including noise reduction, detail smoothing/enhancement, HDR compression, image matting/feathering, haze removal, and joint upsampling. 1

Figure 1: Two views of the graph of the same edge-avoiding wavelet centered at the shoulder of the Cameraman. The support of the wavelet is confined within the limits set by the strong edges around the upper body. We propose a new family of second-generation wavelets constructed using a robust data-prediction lifting scheme. The support of these new wavelets is constructed based on the edge content of the image and avoids having pixels from both sides of an edge. Multi-resolution analysis, based on these new edge-avoiding wavelets, shows a better decorrelation of the data compared to common linear translation-invariant multi-resolution analyses. The reduced inter-scale correlation allows us to avoid halo artifacts in band-independent multi-scale processing without taking any special precautions. We thus achieve nonlinear data-dependent multiscale edge-preserving image filtering and processing at computation times which are linear in the number of image pixels. The new wavelets encode, in their shape, the smoothness information of the image at every scale. We use this to derive a new edge-aware interpolation scheme that achieves results, previously computed by solving an inhomogeneous Laplace equation, through an explicit computation. We thus avoid the difficulties in solving large and poorly-conditioned systems of equations. We demonstrate the effectiveness of the new wavelet basis for various computational photography applications such as multi-scale dynamic-range compression, edge-preserving smoothing and detail enhancement, and image colorization.

Figure 1: L0 smoothing accomplished by global small-magnitude gradient removal. Our method suppresses low-amplitude details. Meanwhile it globally retains and sharpens salient edges. Even the high-contrast thin edges on the tower are preserved. We present a new image editing method, particularly effective for sharpening major edges by increasing the steepness of transition while eliminating a manageable degree of low-amplitude structures. The seemingly contradictive effect is achieved in an optimization framework making use of L0 gradient minimization, which can globally control how many non-zero gradients are resulted in to approximate prominent structure in a sparsity-control manner. Unlike other edge-preserving smoothing approaches, our method does not depend on local features, but instead globally locates important edges. It, as a fundamental tool, finds many applications and is particularly beneficial to edge extraction, clip-art JPEG artifact removal, and non-photorealistic effect generation.

We propose a new model for detail that inherently captures oscillations, a key property that distinguishes textures from individual edges. Inspired by techniques in empirical data analysis and morphological image analysis, we use the local extrema of the input image to extract information about oscillations: We define detail as oscillations between local minima and maxima. Building on the key observation that the spatial scale of oscillations are characterized by the density of local extrema, we develop an algorithm for decomposing images into multiple scales of superposed oscillations. Current edge-preserving image decompositions assume image detail to be low contrast variation. Consequently they apply filters that extract features with increasing contrast as successive layers of detail. As a result, they are unable to distinguish between highcontrast, fine-scale features and edges of similar contrast that are to be preserved.We compare our results with existing edge-preserving image decomposition algorithms and demonstrate exciting applications that are made possible by our new notion of detail.

Figure 1: Our camera and flash system offers dazzle-free photography by hiding the flash in the non-visible spectrum. A pair of images are captured at a blur-free shutter speed, one using a multi-spectral flash (F), the other using ambient illumination (A) which in this case is 1/100th of that required for a correct exposure. The pair are combined to give an output image (R) which is of comparable quality to a reference long exposure shot (L). The figures in this paper are best viewed on screen, rather than in print. Camera flashes produce intrusive bursts of light that disturb or daz-zle. We present a prototype camera and flash that uses infra-red and ultra-violet light mostly outside the visible range to capture pictures in low-light conditions. This “dark ” flash is at least two orders of magnitude dimmer than conventional flashes for a comparable exposure. Building on ideas from flash/no-flash photography, we capture a pair of images, one using the dark flash, other using the dim ambient illumination alone. We then exploit the correlations between images recorded at different wavelengths to denoise the ambient image and restore fine details to give a high quality result, even in very weak illumination. The processing techniques can also be used to denoise images captured with conventional cameras.

The Laplacian pyramid is ubiquitous for decomposing images into multiple scales and is widely used for image analysis. However, because it is constructed with spatially invariant Gaussian kernels,

Recent developments in computational imaging and restoration have heralded the arrival and convergence of several powerful methods for adaptive processing of multidimensional data. Examples include moving least square (from graphics), the bilateral filter (BF) and anisotropic diffusion (from computer vision), boosting, kernel, and spectral methods (from machine learning), nonlocal means (NLM) and its variants (from signal processing), Bregman iterations (from applied math), kernel regression, and iterative scaling (from statistics). While these approaches found their inspirations in diverse fields of nascence, they are deeply connected. Digital Object Identifier 10.1109/MSP.2011.2179329 Date of publication: 5 December 2012 In this article, I present a practical and accessible framework to understand some of the basic underpinnings of these methods, with the intention of leading the reader to a broad understanding of how they interrelate. I also illustrate connections between these techniques and more classical (empirical) Bayesian approaches. The proposed framework is used to arrive at new insights and methods, both practical and theoretical. In particular, several novel optimality properties of algorithms in wide use such as block-matching and three-dimensional (3-D) filtering (BM3D), and methods for their iterative improvement (or nonexistence thereof) are discussed. A general approach is laid out to enable the performance analysis and subsequent improvement of many existing filtering algorithms. While much of the material discussed is applicable to the wider class of linear degradation models beyond noise (e.g., blur,) to keep matters focused, we consider the problem of denoising here.

In landscape photography, distant objects often appear blurred with a blue color cast, a degradation caused by atmospheric haze. To enhance image contrast, pleasantness and information content, dehazing can be performed. We propose that fusing a visible and an near-infrared (NIR) image of the same scene results in a dehazed color image without the need for haze or airlight detection or the generation of depth maps. This is achieved through a multiresolution approach using edge-preserving filtering to minimize artifacts. The near-infrared part of the spectrum is easy to acquire with normal digital cameras. The NIR images are generally devoid of haze as it is an inherent function of the wavelengths. Experiments on real images validate our approach.

Abstract Image matting is of great importance in both computer vision and graphics applications. Most exist-ing state-of-the-art techniques rely on large sparse matri-ces such as the matting Laplacian [12]. However, solving these linear systems is often time-consuming, which is un-favored for the user interaction. In this paper, we propose a fast method for high quality matting. We first derive an effi-cient algorithm to solve a large kernel matting Laplacian. A large kernel propagates information more quickly and may improve the matte quality. To further reduce running time, we also use adaptive kernel sizes by a KD-tree trimap seg-mentation technique. A variety of experiments show that our algorithm provides high quality results and is 5 to 20 times faster than previous methods. 1.