Exploiting redundancy to solve the Poisson equation using local information

Hassan, Firas; Vytla, Lavanya; Carletta, Joan

doi:10.1109/icip.2009.5414119

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This gradient domain compression algorithm is computationally very expensive, as it seeks to solve Poisson equation. The authors of [172] developed a local Fattal's operator to solve the Poisson equation locally and repeatedly, thus making it parallelize-able there by executable in real-time. The modified Poisson solver uses only local information from pixel and its 3 × 3 window neighbors, for computing a tone mapped pixel independent of Fattal's operator on other pixel locations with in the window.…”

Section: Field Programmable Gate Arraymentioning

confidence: 99%

Real-time Tone Mapping: A State of the Art Report

Ou,

Ambalathankandy,

Ikebe

et al. 2020

Preprint

View full text Add to dashboard Cite

The rising demand for high quality display has ensued active research in high dynamic range (HDR) imaging, which has the potential to replace the standard dynamic range imaging. This is due to HDR's features like accurate reproducibility of a scene with its entire spectrum of visible lighting and color depth. But this capability comes with expensive capture, display, storage and distribution resource requirements. Also, display of HDR images/video content on an ordinary display device with limited dynamic range requires some form of adaptation. Many adaptation algorithms, widely known as tone mapping operators, have been studied and proposed in the last few decades. In this state of the art report, we present a comprehensive survey of 50+ tone mapping algorithms that have been implemented on hardware for acceleration and real-time performance. These algorithms have been adapted or redesigned to make them hardware-friendly. This effort leads to various design challenges that are encountered during the hardware development. Any real-time application poses strict timing constraints which requires time exact processing of the algorithm. Also, most of the embedded systems would have limited system resources in terms of battery, computational power and memory resources. These design challenges require novel solutions, and in this report we focus on these issues.In this we survey will discuss those tonemap algorithms which have been implemented on GPU [1-10], FPGA , and ASIC [42][43][44][45][46][47][48][49][50][51][52][53] in terms of their hardware specifications and performance. Output image quality is an important metric for tonemap algorithms. From our literature survey we found that, various objective quality metrics have been used to demonstrate the functionality of adapting the algorithm on hardware platform. We have compiled and studied all the metrics used in this survey [54][55][56][57][58][59][60][61][62][63][64][65][66][67]. Finally, in this report we demonstrate the link between hardware cost and image quality thereby illustrating the underlying trade-off. This report concludes with a discussion on the general future research directions based-on various hardware design/implementation bottlenecks which will be useful for the research community.

show abstract

Section: Field Programmable Gate Arraymentioning

confidence: 99%

Real-time Tone Mapping: A State of the Art Report

Ou,

Ambalathankandy,

Ikebe

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…22 product; here, the b value is 0.9, and the mantissa is normalized to be between 0.5 and 1, so the output power term is between 1.000 and 1.072. This means that the output of the (6,-6) m 3 u,v (6,-6) m 4 u,v (6,-6) The second lookup table is the exponent lookup table and is indexed by the sum of the exponents. Each of the exponents has four bits; when all the exponents are added together, the final sum of the exponents has seven bits to avoid the possibility of any overflow.…”

Section: Attenuation Factor Computationmentioning

confidence: 99%

“…The HDR local TMO proposed in the thesis relies on a novel technique for solving the Poisson equation. Our local Poisson solver [3] gives hardware that is independent of image size, and amenable to real-time implementation. Rather than work with the entire image at once to find the complete output image, our local Poisson solver finds one pixel of the output image at a time, considering it to be the center pixel in a 3×3…”

mentioning

confidence: 99%

See 1 more Smart Citation

A real-time implementation of gradient domain high dynamic range compression using a local Poisson solver

Vytla

Hassan

Carletta

2011

J Real-Time Image Proc

Self Cite

View full text Add to dashboard Cite

This thesis presents a real-time hardware implementation of a gradient domain high dynamic range compression algorithm; this technique is useful for processing high dynamic range (HDR) images to be able to view them on standard display devices. The hardware implementation is described in VHDL and synthesized for a field programmable gate array (FPGA) device. The maximum operating frequency achieved is fast enough to process high dynamic range videos with one megapixel per frame at a rate of about 100 frames per second. The hardware is tested on standard HDR images from the Debevec library. The output images have good visual quality and are similar to the output images obtained using floating-point arithmetic. An alternate hardware implementation that does not involve any multipliers is also discussed. The inverse gradient transformation required for reconstructing back the image from the manipulated gradients is implemented by means of a local Poisson solver that utilizes only local information around each pixel along with special boundary conditions. The local Poisson solver requires a small and fixed amount of hardware and memory for any image size. The quality of the images obtained using our local Poisson solver for both fixed-point and floating-point implementations is compared to the quality of images produced by a system that solves the Poisson equation using a full-image fast Fourier transform (FFT).

show abstract

An adaptive dynamic range compression with local contrast enhancement algorithm for real-time color image enhancement

Tsai

2012

J Real-Time Image Proc

View full text Add to dashboard Cite

Exploiting redundancy to solve the Poisson equation using local information

Cited by 6 publications

References 12 publications

Real-time Tone Mapping: A State of the Art Report

Real-time Tone Mapping: A State of the Art Report

A real-time implementation of gradient domain high dynamic range compression using a local Poisson solver

An adaptive dynamic range compression with local contrast enhancement algorithm for real-time color image enhancement

Contact Info

Product

Resources

About