Gaussian Fourier Pyramid for Local Laplacian Filter

Sumiya, Yuto; Otsuka, Tomoki; Maeda, Yuji; Fukushima, Norishige

doi:10.1109/lsp.2021.3121198

Cited by 12 publications

(7 citation statements)

References 34 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed Winograd filtering devices 𝐹(2 × 2,5 × 5) consist of 6 DTR devices, 36 MUL devices and 2 FTR devices. Thus, the parameters of the proposed device modulo 2 𝛼 , based on (26), (30) and (32), are The proposed signal filtering device was compared with a device for filtering by the Winograd method without using RNS [29]. In addition, a comparison was made with a filtering device consisting of multiply-accumulation units (MAC) [30], and a device consisting of truncated multiplyaccumulation units (TMAC) without RNS arithmetic [31] and with RNS [28].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Digital Filter Architecture Based on Modified Winograd Method F(2× 2, 5× 5) and Residue Number System

et al. 2023

View full text Add to dashboard Cite

Improving the characteristics of digital signal processing devices is an important task in many practical problems. The paper proposes the architecture of a two-dimensional digital filter with a 5 × 5 mask, in which calculations are performed according to the Winograd method in the Residue Number System (RNS) with moduli of a special type. Theoretical analysis and hardware Field-Programmable Gate Array simulation are presented. The results show that the fragment throughput fr/s (number of fragments per second) of the device is 29.6% -724.7% higher than state-of-the-art solutions. This is achieved by the combination of the Winograd method, which reduces the number of multiplications, with the RNS arithmetic, which performs addition and multiplication under smaller operands in parallel. However, our experiments showed that the proposed method requires up to 2.54% -11.01% more Look-Up Tables and 3.58% -19.83% higher power consumption compared to known analogues.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The proposed filter architectures can be applied to digital filters for edge detection [32,33] and smoothing [34], discrete wavelet transform [35], and to implement the convolution operation in the convolutional layer of the convolutional neural network [36].…”

Section: Discussionmentioning

confidence: 99%

Digital Filter Architecture Based on Modified Winograd Method F(2× 2, 5× 5) and Residue Number System

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Using edge-preserving filtering, ( 13 ) of the final step is replaced as:

where

represents any joint edge-preserving filtering with the guidance signal set as

. Examples of the final step filtering are high-dimensional filtering (high-dimensional Gaussian filtering [ 47 , 48 ], guided image filtering [ 20 , 71 ], domain transform filtering [ 33 ], adaptive manifold filtering [ 30 ]), frequency transform filtering ( edge-avoiding wavelet [ 72 , 73 ], redundant frequency transform [ 74 ]), adaptive filtering (range parameter adaptive filtering [ 75 ]), enhancement filtering (local Laplacian filtering [ 76 , 77 , 78 ]), statical filtering (fast guided median filtering [ 79 ]), LUT-based filtering [ 80 ], optimization-based filtering (weighted least square optimization [ 81 , 82 ], and L0 smoothing optimization [ 83 ]).…”

Section: Extension Of Decomposed Multilateral Filteringmentioning

confidence: 99%

Decomposed Multilateral Filtering for Accelerating Filtering with Multiple Guidance Images

Nogami,

Kanetaka,

Naganawa

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

This paper proposes an efficient algorithm for edge-preserving filtering with multiple guidance images, so-called multilateral filtering. Multimodal signal processing for sensor fusion is increasingly important in image sensing. Edge-preserving filtering is available for various sensor fusion applications, such as estimating scene properties and refining inverse-rendered images. The main application is joint edge-preserving filtering, which can preferably reflect the edge information of a guidance image from an additional sensor. The drawback of edge-preserving filtering lies in its long computational time; thus, many acceleration methods have been proposed. However, most accelerated filtering cannot handle multiple guidance information well, although the multiple guidance information provides us with various benefits. Therefore, we extend the efficient edge-preserving filters so that they can use additional multiple guidance images. Our algorithm, named decomposes multilateral filtering (DMF), can extend the efficient filtering methods to the multilateral filtering method, which decomposes the filter into a set of constant-time filtering. Experimental results show that our algorithm performs efficiently and is sufficient for various applications.

show abstract

“…HDKF has various image processing applications. HDKFs are used in various image processing applications, such as denoising [17], deblurring [18], detail enhancement [19] and manipulation [20], high-dynamicrange imaging [21], [22], haze removal [23], low-light image manipulation [24], alpha matting [25], stereo matching [26], and optical flow estimation [27].…”

Section: Introductionmentioning

confidence: 99%

SIMD-Constrained Lookup Table for Accelerating Variable-Weighted Convolution on x86/64 CPUs

Naganawa,

Kamei,

Kanetaka

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Convolution is the inner product of the neighborhood signal and weights and plays a fundamental role in image processing; thus, acceleration of convolution is essential. Among convolutions, variable-weighted convolution is used in adaptive filters and edge-preserving smoothing to realize various applications. Some weights are replaced with lookup tables (LUTs) to accelerate these filters. LUT reference is a classical acceleration method. However, the difference between the growth rate in computing speed and memory I/O speed has limited the scope of utilization of LUT references. Speedup would be possible if registers could be used as LUTs, but their small size makes them difficult to utilize. Therefore, this study proposes a downsampling method to fit LUTs into SIMD registers, which are relatively large and an efficient reference method for register-LUTs. Experimental results show that the proposed method can reproduce an accuracy in PSNR of 65.52 (+25.11) dB, while a simple full-size LUT in the register size can only reproduce 40.41 dB. Using a wider register width, the PSNR was 78.63 (+38.22) dB with AVX-512 and 84.5 (+44.09) dB with bfloat16. The fastest proposed method was on average 4.82/3.72 times faster than direct vector computing, 2.99/3.10 times faster than vector addressing, and 3.79/7.80 times faster than scalar addressing on the AVX2/AVX-512 computers while exceeding the display limit of 60 dB for 8-bit displays. Taking into account these speed/accuracy trade-offs, the performance of the proposed method was superior. This paper shows that LUT references can be realized with small SIMD registers in convolution. The proposed method is expected to be extended to adaptive filters, convolutional neural networks, and other image processing applications by accelerating the approximation with this register-LUT. Our code is available at https://fukushimalab.github.io/registerLUT4conv/.

show abstract

Gaussian Fourier Pyramid for Local Laplacian Filter

Cited by 12 publications

References 34 publications

Digital Filter Architecture Based on Modified Winograd Method F(2× 2, 5× 5) and Residue Number System

Digital Filter Architecture Based on Modified Winograd Method F(2× 2, 5× 5) and Residue Number System

Decomposed Multilateral Filtering for Accelerating Filtering with Multiple Guidance Images

SIMD-Constrained Lookup Table for Accelerating Variable-Weighted Convolution on x86/64 CPUs

Contact Info

Product

Resources

About