An FPGA-Based Fully Pipelined Bilateral Grid for Real-Time Image Denoising

Hashimoto, Nobuho; Takamaeda-Yamazaki, Shinya

doi:10.1109/fpl53798.2021.00035

Cited by 5 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In study [7], a real-time image denoising system that uses an FPGA based on the bilateral grid (BG) had been proposed. The bilateral gird (BG) structure is shown as Fig 2 . Firstly, the input image pixels p(x, y) are read from DRAM one by one using the AXI bus and DMA.…”

Section: Fully Pipelined Bilateral Gridmentioning

confidence: 99%

“…To simplify the hardware design, two one-dimensional filters were adopted for gray filtering instead of two-dimensional filters, resulting in a significant reduction in hardware design complexity. In [7], a bilateral grid with variable-sized windows was implemented by introducing a window radius parameter, effectively restraining the growth of hardware resources as the window size increases. A novel solution that facilitates intra image content-adaptive bilateral filtering by modulating range and space sigma through virtual sub-tables was proposed in [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A real time hardware design for bilateral filtering

Jin

2024

ACE

View full text Add to dashboard Cite

Bilateral filtering is a widely used video image filtering method, but its computational complexity is high, which is not conducive to hardware real-time applications. Therefore, this paper presents a hardware structure of bilateral filtering for real-time applications of high-definition images. Our hardware design mainly includes lookup table structure and parallel structure designs, respectively. Based on the Vivado HLS evaluation, the experimental results show that the hardware structure of this paper can meet the real-time application of bilateral filtering in high-definition video images.

show abstract

Section: Fully Pipelined Bilateral Gridmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A real time hardware design for bilateral filtering

Jin

2024

ACE

View full text Add to dashboard Cite

show abstract

“…A continuous sequence of comparing an image assumption with the real-time measured values for this method made it almost impossible for the early scanners to perform [24]. However, with the rapid advancement of computer technology, this technique can now be handled and can achieve higher image quality in terms of the image texture and spatial resolution [26]. Learned experts' assessment-based reconstruction network (LEARN) is introduced, which utilizes the regularization and parameters used during the IR training process to effectively recover the images while attempting to reduce the computational costs [27].…”

Section: Pre-reconstructionmentioning

confidence: 99%

Fused Attention Modules Embedded in Artificial Neural Networks for Low Dose CT Denoising With Integrated Loss Functions

Marcos

2024

Preprint

View full text Add to dashboard Cite

<p>X-ray Computed Tomography (CT) is a non-invasive medical diagnostic tool that has raised public concerns due to the associated health risks of radiation dose to patients. Reducing the radiation dose leads to noise artifacts, making the low-dose CT images unreliable for diagnosis. Hence, low-dose computed tomography (LDCT) image reconstruction techniques have offered a new challenge in the research area. This thesis focuses on reconstructing LDCT images using deep learning techniques to provide an efficient, effective, and accurate training regimes for LDCT image denoising. A fusion of spatial and channel attention modules integrated into a dilated residual network is proposed to improve the structural details of denoised LDCT images. Further, a combination of perceptual loss, per-pixel loss, and structural dissimilarity loss is used for the optimization of the overall network. These objective functions aim to preserve structural details, avoid edge over-smoothing and enhance the image texture, respectively. Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Metrics (SSIM) are used for measuring the quantitative results. A comparative experiment was done between the proposed model and the recent denoising models, such as Block Matching and 3D Filtering (BM3D), patch Markovnian Generative Adversarial Network (patch-GAN) and dilated residual learning with edge detection (DRL-E-MP). Not only with quantitative results, but these models were also compared visually. To further strengthen the validity of the outcomes, five different CT image datasets were used. The proposed model obtained the highest PSNR/SSIM value of 34.36/0.6971 while BM3D resulted in the lowest value with 30.24/0.4461 using the chest dataset from the Mayo Clinic. Overall, the proposed network demonstrated that it could outperform state-of-the-art models.</p>

show abstract

Image-Adaptive 3D Lookup Tables for Real-Time Image Enhancement with Bilateral Grids

Kim,

Cho

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

An FPGA-Based Fully Pipelined Bilateral Grid for Real-Time Image Denoising

Cited by 5 publications

References 25 publications

A real time hardware design for bilateral filtering

A real time hardware design for bilateral filtering

Fused Attention Modules Embedded in Artificial Neural Networks for Low Dose CT Denoising With Integrated Loss Functions

Image-Adaptive 3D Lookup Tables for Real-Time Image Enhancement with Bilateral Grids

Contact Info

Product

Resources

About