Abstract:
영상 강화 시스템, 방법, 및 상기 방법을 실행시키기 위한 컴퓨터 판독 가능한 프로그램을 기록한 기록 매체가 개시된다. 영상 강화 시스템은, 미리 설정된 장파장의 영상 신호에서 산란성분을 완화 처리하는 산란성분 완화 처리부, 및 미리 설정된 예측 모델을 이용하여 산란성분이 완화 처리된 영상 신호를 변환하여 미리 설정된 단파장의 영상 신호인 가상영상 신호를 생성하는 가상영상 변환부를 포함한다. 이와 같은 구성에 의하면, 적외선 신호로부터 광의 산란성분을 완화하고 이를 변환하여 가상의 RGB 영상을 생성함으로써, 짙은 연기속에서도 촬영 대상에 대한 직관적인 영상을 제공할 수 있게 된다.
Abstract:
컴퓨팅 장치를 이용하여 영상을 변환하는 방법이 개시된다. 상기 방법은, 컨텐트에 관한 sRGB(standard Red Green Blue)의 색역(gamut)을 갖는 제1 sRGB 영상을 획득하는 단계; 뉴럴 네트워크를 이용하여 상기 제1 sRGB 영상의 색역을 DCI-P3(Digital Cinema Initiative-P3)의 색역으로 변환한 제1 변환 영상을 획득하는 단계; 상기 제1 sRGB 영상에 제1 색 변환 행렬을 적용함으로써 생성된 제2 변환 영상 및 상기 제1 변환 영상에 기초하여, 상기 제1 sRGB 영상의 색역을 DCI-P3 색역으로 변환한 최종 변환 영상을 생성하는 단계를 포함한다.
Abstract:
Provided is an image pickup apparatus including a multi-band pass filter that selectively transmits band light in a specific band, a color filter that transmits the band light in the specific band per pixel of an image pickup device, the image pickup device that receives light transmitted by the multi-band pass filter and the color filter, and a signal processing section to which a pixel value of the image pickup device is input and which executes a signal process on the pixel value. The multi-band pass filter is configured to selectively transmit band light corresponding to a plurality of color filter elements, and the signal processing section generates a pixel value corresponding to a band, of a pixel to be processed using a raw image base pixel value signal per pixel and a spectral characteristic parameter of the image pickup apparatus.
Abstract:
A video encoder and decoder system includes a video decoder (220) converting in input HDR images in a luma and chrominance representation to SDR images in a luma and subsampled chrominance representation by directly applying dynamic range conversion gains in the luma and subsampled chrominance domain. An video encoder may perform the opposite operation and convert from SDR to HDR by directly applying dynamic range conversion gains in the luma and subsampled chrominance domain.
Abstract:
Techniques for selecting a luminance value for color space conversion are disclosed. Techniques include determining values for Cb and Cr from values for R', G', and B'; producing a reconstructed Cb* value and a reconstructed Cr* value by processing the Cb and Cr values; and determining a plurality of Y' value options from the values for Cb* and Cr*. A Y' output value may be selected based on the plurality of Y' value options.
Abstract:
A method of color mapping a video signal represented in a first color volume from color mapping data to be applied on a video signal represented in a second color volume is disclosed. The method comprises: - color mapping (14) said video signal represented in a first color volume from said first color volume into said second color volume in the case where said first and second color volumes are different; and - color mapping (16) said color mapped video signal based on said color mapping data.
Abstract:
Systems, methods, and instrumentalities are disclosed for color space conversion. A video signal associated with a first color space may be received. The first color space may comprise a point. A partition of the first color space that includes the point may be determined. The partition may be associated with a first dimensionality. The point may be converted from the first color space to a second color space using a color space conversion model that corresponds with the partition. The color space conversion model may be associated with a second dimensionality. The second dimensionality may be less than the first dimensionality.
Abstract:
A display management processor receives an input image with enhanced dynamic range to be displayed on a target display which has a different dynamic range than a reference display. The input image is first transformed into a perceptually-corrected IPT color space. A non-linear mapping function generates a first tone-mapped signal by mapping the intensity of the input signal from the reference dynamic range into the target dynamic range. The intensity (I) component of the first tone-mapped signal is sharpened to preserve details, and the saturation of the color (P and T) components is adjusted to generate a second tone-mapped output image. A color gamut mapping function is applied to the second tone-mapped output image to generate an image suitable for display onto the target display. The display management pipeline may also be adapted to adjust the intensity and color components of the displayed image according to specially defined display modes.
Abstract:
Systems, apparatus, articles, and methods are described including operations for color enhancement via gamut expansion, comprising: detecting an extent of colorfulness based at least in part on a histogram associated with an input color space; determining a virtual color space based at least in part on the detected extent of colorfulness associated with the input color space; and transforming input data from the input color space to the virtual color space via absolute colorimetric mapping.