Abstract: Provided is a two-dimensional (2D) image processing method including obtaining a 2D image, processing the obtained 2D image by using a trained convolutional neural network (CNN) to obtain at least one camera parameter and at least one face model parameter from the 2D image, and generating a three-dimensional (3D) face model, based on the obtained at least one camera parameter and at least one face model parameter.

Abstract: A method for training a convolutional neural network to reconstruct an image. The method includes forming a common loss function basing on the left and right images (IL, IR), reconstructed left and right images (I?L, I?R), disparity maps (dL, dR), reconstructed disparity maps (d?L, d?R) for the left and right images (IL, IR) and the auxiliary images (I?L, I?R) and training the neural network based on the formed loss function.

Abstract: Provided is a two-dimensional (2D) image processing method including obtaining a 2D image, processing the obtained 2D image by using a trained convolutional neural network (CNN) to obtain at least one camera parameter and at least one face model parameter from the 2D image, and generating a three-dimensional (3D) face model, based on the obtained at least one camera parameter and at least one face model parameter.

Abstract: A method for training a convolutional neural network to reconstruct an image. The method includes forming a common loss function basing on the left and right images (IL, IR), reconstructed left and right images (I?L, I?R), disparity maps (dL, dR), reconstructed disparity maps ((d?L, d?R) for the left and right images (IL, IR) and the auxiliary images (I?L, I?R) and training the neural network based on the formed loss function.

Abstract: A method for training a convolutional neural network to reconstruct an image. The method includes forming a common loss function basing on the left and right images (IL, IR), reconstructed left and right images (I?L, I?R), disparity maps (dL, dR), reconstructed disparity maps (d?L, d?R) for the left and right images (IL, IR) and the auxiliary images (I?L, I?R) and training the neural network based on the formed loss function.

Abstract: An approach is provided to process an image. The approach includes: obtaining a pixel shift set indicating information of movement of a plurality of pixels included in coinciding portions among a plurality of low-resolution images with respect to a single scene; dividing the pixel shift set into an integer portion and a fractional portion; generating an integer pixel shift set and a fractional pixel shift set; selecting a filter set corresponding to the plurality of pixels from among a plurality of pre-stored filter sets including a filter weight value applied to the pixels; and obtaining a high-resolution image with respect to the single scene, based on the plurality of low-resolution images, the selected filter set, and the integer pixel shift set.

Abstract: A system and a method for displaying a scene are provided. The system includes a display configured to emit light, a spatial light modulator configured to modulate input light based on a transparency value, and at least one processor configured to acquire adjustment information including transparency of the spatial light modulator and light intensity information of the display from a plurality of pieces of view information corresponding to the scene and adjust an intensity value of the light emitted from the display and the transparency value of the spatial light modulator based on the adjustment information, wherein the plurality of pieces of view information are optical information of the scene, the optical information having been acquired at a plurality of viewpoints.

Abstract: A method for training a convolutional neural network to reconstruct an image. The method includes forming a common loss function basing on the left and right images (IL, IR), reconstructed left and right images (I?L, I?R), disparity maps (dL, dR), reconstructed disparity maps (d?L, d?R) for the left and right images (IL, IR) and the auxiliary images (I?L, I?R) and training the neural network based on the formed loss function.

Abstract: A system and a method for displaying a scene are provided. The system includes a display configured to emit light, a spatial light modulator configured to modulate input light based on a transparency value, and at least one processor configured to acquire adjustment information including transparency of the spatial light modulator and light intensity information of the display from a plurality of pieces of view information corresponding to the scene and adjust an intensity value of the light emitted from the display and the transparency value of the spatial light modulator based on the adjustment information, wherein the plurality of pieces of view information are optical information of the scene, the optical information having been acquired at a plurality of viewpoints.

Abstract: An approach is provided to process an image. The approach includes: obtaining a pixel shift set indicating information of movement of a plurality of pixels included in coinciding portions among a plurality of low-resolution images with respect to a single scene; dividing the pixel shift set into an integer portion and a fractional portion; generating an integer pixel shift set and a fractional pixel shift set; selecting a filter set corresponding to the plurality of pixels from among a plurality of pre-stored filter sets including a filter weight value applied to the pixels; and obtaining a high-resolution image with respect to the single scene, based on the plurality of low-resolution images, the selected filter set, and the integer pixel shift set.