Luminance CDF Mapping for Single-Image HDR Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for converting Low Dynamic Range (LDR) images to High Dynamic Range (HDR) images either result in ghost artifacts when combining multiple images or introduce noise and distortion, and are time-consuming and costly, as they require multiple non-moving images or linear expansion of a single image's luminance.
Innovation Solution
An electronic apparatus and method that uses a processor to calculate new luminance values based on cumulative distribution functions, applying a predetermined conversion relation obtained through deep-learning to expand the dynamic range of LDR images, generating a new HDR image with improved contrast ratio without the need for multiple images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If multiple LDR images are combined to create HDR image, then dynamic range is improved, but ghost artifacts occur and processing time increases
Solution Approach 1:
The patent transforms the LDR image to HDR by changing the luminance parameter distribution through cumulative distribution function mapping. The luminance values are transformed using the relationship between the CDF of the LDR image and a target CDF, effectively expanding the dynamic range from a limited luminance scale to a wider HDR luminance scale without requiring multiple images.
2Loss of time
If linear luminance expansion is applied to single LDR image, then processing time is reduced, but noise and distortion increase
Solution Approach 1:
The patent employs a feedback mechanism by using the cumulative distribution function of the input LDR image itself as part of the transformation process. The target luminance values are determined by mapping the source CDF to a target CDF, where the transformation adapts to the specific luminance distribution of the input image, thereby reducing noise and distortion compared to fixed linear expansion methods.
3Illumination intensity
If multiple LDR images are required for HDR conversion, then dynamic range is improved, but cost and complexity increase
Solution Approach 1:
The patent extracts and utilizes the cumulative distribution function characteristics from the single LDR image to perform HDR conversion. By extracting the CDF information and using it to drive the luminance transformation, the method eliminates the need to acquire and process multiple separate images, thereby reducing system complexity and acquisition costs while maintaining HDR capabilities.
Data Source
AI summary
An electronic apparatus includes a memory configured to store a predetermined conversion relation, and a processor configured to obtain first luminance information indicating luminance values of respective pixels included in a first image, and obtain first color information indicating color values of the respective pixels, obtain a first cumulative distribution function indicating a relation between a cumulative pixel count and each luminance level based on the first luminance information, obtain a second cumulative distribution function by applying the predetermined conversion relation to the first cumulative distribution function, calculate second luminance information indicating converted luminance values of the respective pixels by using the first cumulative distribution function and the second cumulative distribution function, and generate a second image based on the first color information and the second luminance information.