Unlock instant, AI-driven research and patent intelligence for your innovation.

Detail-preserving high fidelity tone mapping method

A tone mapping, high-fidelity technology, applied in the field of image processing, can solve the problems of inaccurate detail layers, low-fidelity LDR images, inability to effectively control the intensity of tone compression, etc., to achieve good visual effects, high implementation efficiency, well-structured effect

Active Publication Date: 2017-05-24
SHANGHAI UNIV
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the detail layer obtained by these methods does not fully consider the local correlation of the HDR image, and cannot effectively control the intensity of tone compression, so the obtained detail layer is not accurate, and some visual defects may appear. Realistic LDR image

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Detail-preserving high fidelity tone mapping method
  • Detail-preserving high fidelity tone mapping method
  • Detail-preserving high fidelity tone mapping method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] Preferred embodiments of the present invention are described as follows in conjunction with the accompanying drawings:

[0060] see figure 1 , a detail-preserving high-fidelity tone mapping method, the specific steps are as follows:

[0061] (1) Use the k-means clustering algorithm to preprocess the high dynamic range image to generate k color clusters, and then use the average value of each cluster to replace the value of each pixel in the corresponding cluster to obtain the initial hue layer, the specific steps are as follows:

[0062] (a) Randomly select k cluster centroid points as μ 1 , μ 2 ,…, μ k ∈R n ;

[0063] (b) Repeat the following process until convergence:

[0064] For each pixel i, calculate the class it should belong to:

[0065]

[0066] For each class j, recalculate the centroid of that class:

[0067]

[0068] where k is a given clustering constant, C (i) Represents the closest class between pixel i and k clusters, centroid μ i Repres...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a detail-preserving-based high fidelity tone mapping method. The method comprises steps that (1), a k-means clustering algorithm is utilized to pre-process high dynamic range images to generate K color clusters, an average value of each cluster is utilized to replace a value of each pixel point of the corresponding cluster to acquire an initial tone layer; (2), an image decomposition algorithm is utilized to extract an initial detail layer, an affinity concept is defined, and a detail affinity factor is constructed to optimize the detail layer; (3), color edition processing on corresponding low dynamic range images is carried out, and a gradient guiding method is then utilized to reconstruct a new tone layer; and (4), the optimized detail layer and the reconstructed tone layer are merged to lastly acquire a high fidelity tone mapping result. The method has advantages of intelligible flow, complete structure and high realization efficiency.

Description

technical field [0001] The invention relates to a detail-preserving high-fidelity tone mapping method, which belongs to the field of image processing. Background technique [0002] In real scenes, the distribution of brightness values ​​is very wide. In the case of direct sunlight, the scene brightness can reach 10 5 cd / m 2 , and the brightness value in the dark may only be 10 -3 cd / m 2 . Generally speaking, the dynamic range of brightness accepted by the human visual system in the same scene is about 10000:1. At present, most conventional display devices only support display output with a lower dynamic range (generally only 1-100cd / m 2 ), this range does not match the high dynamic range (High Dynamic Range, HDR) image, direct display will cause the original rich image brightness information to be lost, resulting in poor visual effects, details are not obvious, and it is impossible to accurately obtain detailed information and target identify. HDR images can represen...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06T5/50
CPCG06T5/50G06T2207/20221G06T2207/20208G06F18/23213
Inventor 杜胜唐仕郭雨辰谢志峰黄东晋丁友东
Owner SHANGHAI UNIV