Real-time O(1) bilateral filtering

Yang, Qingxiong; Tan, Kar-Han; Ahuja, Narendra

doi:10.1109/cvpr.2009.5206542

Cited by 298 publications

(294 citation statements)

References 21 publications

Supporting

Mentioning

293

Contrasting

Unclassified

Order By: Relevance

“…More elaborate fusion techniques such as the multi-lateral filter for real-time depth enhancement presented in [30] can certainly be considered. However, real-time in depth enhancement has been possible by considering the recent fast implementation techniques for bilateral filtering [31], [32], [33] in which the data to be filtered must be downsampled. This is the main reason why we propose a backward warping approach that generates a dense depth map instead of the sparse depth map generated using forward warping.…”

Section: Discussionmentioning

confidence: 99%

Real-Time Distance-Dependent Mapping for a Hybrid ToF Multi-Camera Rig

Garcia

Aouada

Mirbach

et al. 2012

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Abstract-We propose a real-time mapping procedure for data matching to deal with hybrid ToF multi-camera rig data fusion. Our approach takes advantage of the depth information provided by the ToF camera to calculate the distance-dependent disparity between the two cameras that constitute the system. As a consequence, the not co-centric binocular system behaves as a co-centric system with co-linear optical axes between their sensors. The association between mapped and non-mapped image coordinates can be described by a set of look-up tables. This, in turn, reduces the complexity of the whole process to a simple indexing step, and thus, performs in real-time. The experimental results show that in addition to being straightforward and easy to compute, our proposed data matching approach is highly accurate which facilitates further fusion operations.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-Time Distance-Dependent Mapping for a Hybrid ToF Multi-Camera Rig

Garcia

Aouada

Mirbach

et al. 2012

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…As can be seen, the proposed smoothing method produces comparable smoothing quality at lower computational cost. Note that the results presented here are produced (a) Input (b) Fast BLF [7] (c) RF [11] (d) AdaptM [12] (e) Proposed (1 iteration with the original Local Laplacian Filter implementation that is computationally very demanding. The Fast Local Laplacian Filters method [18] that aims at making the Local Laplacian Filter faster is only an approximation and does not produce comparable smoothing quality.…”

Section: Smoothing Quality Comparisonmentioning

confidence: 99%

“…We evaluate the quality and speed of 3 fast edgeaware filters : the fast implementation of the bilateral filter in [7], the domain transform method (RF filter) in [11] and the adaptive manifolds method in [12]. We use the following setup : Intel Xeon CPU E5-2609 2.24 GHz, Matlab 2013a on Linux 64bits and an Intel i7-2670QM 2.20Ghz on Windows 7.…”

Section: Fast Smoothing Comparisonmentioning

confidence: 99%

“…A naive implementation of this filter is computationally demanding as it operates in a high-dimension space. Many researchers tried to boost this filter or at least simulate bilaterallike results by either using linear interpolation [3], optimized data structures such as the bilateral grid [4], reformulation and downsampling [5], [6], constant time spatial filters decomposition [7], Gaussian KDtrees [8], Supports Vector Machines regression [9], recursive implementation [10], dimensionality reduction [11], adaptive manifolds [12], among others. The bilateral filter is the building block of a wide range of applications such as HDR tone-mapping [3], nonphotorealistic rendering [13], upsampling [14] and non-blind image deconvolution [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Edge-Aware Processing via First Order Proximal Approximation

Badri

Yahia

Aboutajdine³

2015

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-We present a new framework for fast edge-aware processing of images and videos. The proposed smoothing method is based on an optimization formulation with a non-convex sparse regularization for a better smoothing behavior near strong edges. We develop mathematical tools based on first order approximation of proximal operators to accelerate the proposed method while maintaining high-quality smoothing. The first order approximation is used to estimate a solution of the proximal form in a half-quadratic solver, and also to derive a warm-start solution that can be calculated quickly when the image is loaded by the user. We extend the method to large-scale processing by estimating the smoothing operation with independent 1D convolution operations. This approach linearly scales to the size of the image and can fully take advantage of parallel processing. The method supports full color filtering and turns out to be temporally coherent for fast video processing. We demonstrate the performance of the proposed method on various applications including image smoothing, detail manipulation, HDR tone-mapping, fast edge simplification and video edge-aware processing.

show abstract

“…In fact, one would expect ω to scale with the image size in most applications of the bilateral filter [9]. Several fast algorithms have been proposed that offer various trade-offs between speed and accuracy [6,8,10,13,4,11,3,1,2,7]. We refer the interested reader to these recent papers [11,3] for a survey and comparison of various fast algorithms.…”

Section: Introductionmentioning

confidence: 99%

A Fast Approximation of the Bilateral Filter using the Discrete Fourier Transform

Nair¹,

Popli²,

Chaudhury³

2017

Image Processing on Line

View full text Add to dashboard Cite

The bilateral filter is a popular non-linear smoother that has applications in image processing, computer vision, and computational photography. The novelty of the filter is that a range kernel is used in tandem with a spatial kernel for performing edge-preserving smoothing, where both kernels are usually Gaussian. A direct implementation of the bilateral filter is computationally expensive, and several fast approximations have been proposed to address this problem. In particular, it was recently demonstrated in a series of papers that a fast and accurate approximation of the bilateral filter can be obtained by approximating the Gaussian range kernel using polynomials and trigonometric functions. By adopting some of the ideas from this line of work, we propose a fast algorithm based on the discrete Fourier transform of the samples of the range kernel. We develop a parallel C implementation of the resulting algorithm for Gaussian kernels, and analyze the effect of various extrinsic and intrinsic parameters on the approximation quality and the run time. A key component of the implementation are the recursive Gaussian filters of Deriche and Young. Source CodeThe ANSI C source code used in the demo can be downloaded from the web page of this article 1 . Compilation and usage instruction are included in the README.txt of the archive.

show abstract

Real-time O(1) bilateral filtering

Cited by 298 publications

References 21 publications

Real-Time Distance-Dependent Mapping for a Hybrid ToF Multi-Camera Rig

Real-Time Distance-Dependent Mapping for a Hybrid ToF Multi-Camera Rig

Fast Edge-Aware Processing via First Order Proximal Approximation

A Fast Approximation of the Bilateral Filter using the Discrete Fourier Transform

Contact Info

Product

Resources

About