Inverse Tone Mapping for SDR to HDR Image Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack a standardized method to effectively convert standard dynamic range (SDR) images into high dynamic range (HDR) content for enhanced display on HDR devices while preserving the artistic intent and visual quality of the original images.
Innovation Solution
The method involves determining if an SDR image was generated from an HDR image, applying an inverse tone mapping function to transform the SDR image into an HDR image, and adjusting parameter values based on image quality to ensure the dynamic range is increased without distortion, using techniques such as sigmoidal inverse tone mapping and bilateral filtering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If inverse tone mapping is applied to SDR images, then dynamic range is increased for HDR display, but image quality may be distorted or artistic content damaged
Solution Approach 1:
The system performs preliminary detection to determine whether the SDR image was generated from an HDR image before applying inverse tone mapping. This preliminary action prevents distortion of images that should not be converted, thereby protecting image quality while enabling dynamic range expansion for appropriate images.
Solution Approach 2:
The system uses feedback mechanisms by analyzing image characteristics and quality metrics during the conversion process. This feedback allows the system to adjust the inverse tone mapping parameters dynamically, ensuring that artistic content is preserved while achieving the desired dynamic range expansion.
2Adaptability or versatility
If inverse tone mapping function is applied to all SDR images, then HDR content is generated, but processing time and computational resources increase
Solution Approach 1:
The system performs a preliminary detection step to identify which SDR images were originally generated from HDR images. This preliminary action enables selective application of inverse tone mapping only to suitable images, avoiding unnecessary processing of images that would not benefit from conversion, thereby reducing overall processing time.
Solution Approach 2:
Instead of applying inverse tone mapping to all SDR images, the system applies it partially only to images that meet specific criteria (those determined to be generated from HDR images). This partial action approach maintains versatility in HDR content generation while minimizing unnecessary computational overhead.
3Manufacturing precision
If parameter values are adjusted based on image quality, then visual quality is improved, but system complexity increases
Solution Approach 1:
The system changes parameters of the inverse tone mapping function based on detected image characteristics and quality metrics. By dynamically adjusting these parameters, the system improves visual quality of converted images while maintaining a relatively simple overall system architecture through rule-based parameter adjustment.
Data Source
AI summary
Systems, methods, and computer readable media to improve the operation of electronic display systems. Techniques for inverse tone mapping operations for selected standard dynamic range (SDR) images are described. The converted images may be presented on high dynamic range (HDR) displays so as to increase a user's viewing experience (through an expanded dynamic range) while preserving the artistic content of the displayed information. Techniques disclosed herein selectively transform SDR images to HDR images by determining if the SDR images were created from HDR images (e.g., through the fusion of multiple SDR images) and if their quality is such as to permit the conversion without introducing unwanted visual artifacts. The proposed techniques apply a sigmoidal inverse tone mapping function configured to provide a perceptual-based tone mapping. Values for the function's tuning parameters may be set based on what may be determined about the original HDR-to-SDR mapping operation.