Increasing dynamic range of a virtual production display

Abstract

A processor performing postprocessing obtains an input image containing both bright and dark regions. The processor obtains a threshold between a first pixel value of the virtual production display and a second pixel value of the virtual production display. The processor modifies the region according to predetermined steps producing a pattern unlikely to occur within the input image, where the pattern corresponds to a difference between the original pixel value and the threshold. The processor can replace the region of the input image with the pattern to obtain a modified image. The virtual production display can present the modified image. A processor performing postprocessing detects the pattern within the modified image displayed on the virtual production display. The processor calculates the original pixel value of the region by reversing the predetermined steps. The processor replaces the pattern in the modified image with the original pixel value.

1 - 27 . (canceled) 
     
     
         28 . A system comprising:
 at least one hardware processor; and   at least one non-transitory memory storing instructions, which, when executed by the at least one hardware processor, cause the system to:
 obtain an image shown on a display and a pattern to detect in the image; 
 detect the pattern associated with the image,
 wherein the pattern indicates a modified region, and 
 wherein the pattern indicates an expected pixel value of the modified region; 
 
 based on the pattern, determine the expected pixel value of the modified region; 
 replace the pattern in the image with the expected pixel value; and 
 store the expected pixel value. 
   
     
     
         29 . The system of  claim 28 , the instructions to calculate the expected pixel value comprising the instructions to:
 based on the pattern, obtain a function to apply to the modified region; and   calculate the expected pixel value by applying the function to the modified region.   
     
     
         30 . The system of  claim 28 , the instructions to calculate the expected pixel value comprising the instructions to:
 obtain a signature frequency to detect;   detect the signature frequency indicating the modified region;   determine a magnitude of the signature frequency,
 wherein the magnitude of the signature frequency indicates the expected pixel value; and 
   based on the magnitude of the signature frequency, modify a pixel value of the modified region to obtain the expected pixel value.   
     
     
         31 . The system of  claim 28 , comprising instructions to:
 record the pattern from the display;   determine a signature pixel value of the recorded pattern; and   store the signature pixel value of the recorded pattern to use in detecting the pattern within the image presented on the display.   
     
     
         32 . The system of  claim 28 , comprising instructions to:
 detect a second pattern within the image,
 wherein the second pattern indicates a second region surrounding the modified region, 
 wherein a pixel value of the second region has been increased in correspondence to a decrease in a pixel value of the modified region, 
 wherein the second pattern indicates a second expected pixel value associated with the second region; 
   based on the second pattern, calculate the second expected pixel value of the second region,
 wherein the second expected pixel value is lower than the pixel value of the second region; and 
   replace the second pattern in the image with the second expected pixel value.   
     
     
         33 . The system of  claim 28 , comprising the instructions to:
 train a machine learning model to detect a discrepancy between a first image and a second image,
 wherein the first image excludes the pattern, and 
 wherein the second image includes the first image modified with the pattern; and 
   use the machine learning model to detect the pattern within the second image.   
     
     
         34 . The system of  claim 28 , the instructions to detect the pattern comprising the instructions to use a machine learning model to detect the pattern within the image. 
     
     
         35 . The system of  claim 28 , comprising the instructions to: 
 obtain an input indicating a technique among multiple techniques,
 wherein the technique is configured to increase dynamic range of an image recorded from the display; and 
   apply at least a portion of the technique to the image recorded from the display.   
     
     
         36 . A method comprising:
 obtaining an image shown on a display, and a pattern to detect in the image;   obtaining the pattern associated with the image,
 wherein the pattern indicates a modified region, 
 wherein the pattern indicates an expected pixel value of the modified region; 
   based on the pattern, determine the expected pixel value of the modified region;   replacing the pattern in the image with the expected pixel value; and   storing the expected pixel value.   
     
     
         37 . The method of  claim 36 , wherein calculating the expected pixel value comprises:
 obtaining a signature frequency to detect;   detecting the signature frequency indicating the modified region;   determining a magnitude of the signature frequency,
 wherein the magnitude of the signature frequency indicates the expected pixel value; and 
   based on the magnitude of the signature frequency, modifying a pixel value of the modified region to obtain the expected pixel value.   
     
     
         38 . The method of  claim 36 , comprising:
 recording the pattern from the display;   determining a signature pixel value of the recorded pattern; and   storing the signature pixel value of the recorded pattern to use in detecting the pattern within the image presented on the display.   
     
     
         39 . The method of  claim 36 , comprising:
 detecting a second pattern within the image,
 wherein the second pattern indicates a second region surrounding the modified region, 
 wherein a pixel value of the second region has been increased in correspondence to a decrease in a pixel value of the modified region, 
 wherein the second pattern indicates a second expected pixel value associated with the second region; 
   based on the second pattern, calculating the second expected pixel value of the second region, 
 wherein the second expected pixel value is lower than the pixel value of the second region; and 
   replacing the second pattern in the image with the second expected pixel value.   
     
     
         40 . The method of  claim 36 , comprising:
 obtaining an input indicating a technique among multiple techniques,
 wherein the technique is configured to increase dynamic range of an image recorded from the display; and 
   applying at least a portion of the technique to the image recorded from the display.   
     
     
         41 . At least one computer-readable storage medium, excluding transitory signals and carrying instructions, which, when executed by at least one data processor of a system, causes the system to:
 obtain an image shown on a display, and a pattern to detect in the image;   obtain the pattern from the image,
 wherein the pattern indicates a modified region, and 
 wherein the pattern indicates an expected pixel value of the modified region; 
   based on the pattern, determine the expected pixel value of the modified region;   replace the pattern in the image with the expected pixel value; and   store the expected pixel value.   
     
     
         42 . The at least one computer-readable storage medium of  claim 41 , the instructions to calculate the expected pixel value comprising the instructions to:
 obtain a signature frequency to detect;   detect the signature frequency indicating the modified region;   determine a magnitude of the signature frequency,
 wherein the magnitude of the signature frequency indicates the expected pixel value; and 
   based on the magnitude of the signature frequency, modify a pixel value of the modified region to obtain the expected pixel value.   
     
     
         43 . The at least one computer-readable storage medium of  claim 41 , comprising instructions to:
 record the pattern from the display;   determine a signature pixel value of the recorded pattern; and   store the signature pixel value of the recorded pattern to use in detecting the pattern within the image presented on the display.   
     
     
         44 . The at least one computer-readable storage medium of  claim 41 , comprising instructions to:
 detect a second pattern within the image,
 wherein the second pattern indicates a second region surrounding the modified region, 
 wherein a pixel value of the second region has been increased in correspondence to a decrease in a pixel value of the modified region, 
 wherein the second pattern indicates a second expected pixel value associated with the second region; 
   based on the second pattern, calculate the second expected pixel value of the second region,
 wherein the second expected pixel value is lower than the pixel value of the second region; and 
   replace the second pattern in the image with the second expected pixel value.   
     
     
         45 . The at least one computer-readable storage medium of  claim 41 , comprising the instructions to:
 train a machine learning model to detect a discrepancy between a first image and a second image,
 wherein the first image excludes the pattern, and 
 wherein the second image includes the first image modified with the pattern; and 
   use the machine learning model to detect the pattern within the second image.   
     
     
         46 . The at least one computer-readable storage medium of  claim 41 , the instructions to detect the pattern comprising the instructions to use a Fast Fourier Transform to detect the pattern within the image. 
     
     
         47 . The at least one computer-readable storage medium of  claim 41 , comprising the instructions to:
 obtain an input indicating a technique among multiple techniques,
 wherein the technique is configured to increase dynamic range of an image recorded from the display; and 
   apply at least a portion of the technique to the image recorded from the display.