Abstract: A system and method of retrieving metadata, the method comprising: in response to a request from a client for metadata for a set of DICOM instances, loading n DICOM instances of the set of requested DICOM instances; comparing the metadata of the n loaded DICOM instances; generating a common set of values based on the comparison of the n loaded DICOM instances; streaming the common set of values to the client; determining per-instance data for each of the n loaded DICOM instances, the per-instance data being a difference between the metadata of a DICOM instance and the common set of values; transmitting the per-instance data of the loaded DICOM instances to the client; loading additional DICOM instances of the set of requested DICOM instances; determining per-instance data for each of the additional DICOM instances; and transmitting the per-instance data of the additional DICOM instances to the client.

Abstract: A 3D caption display method for harmoniously merging and displaying closed caption with 3D image in a 3D display apparatus, and a 3D display apparatus suitable for implementing the method. The 3D display apparatus receives a broadcast signal containing caption data, and obtains caption control commands including a 3D parameter setting command from the caption data. Afterwards, the 3D display apparatus displays a plurality of 3D caption images according to the caption control commands.

Abstract: A user health monitoring system having 3D glasses and a display apparatus and a display apparatus and a control method thereof, the user health monitoring system including: 3D glasses which obtain biosignal information of a user and transmit; and a display apparatus which receives the biosignal information transmitted by the 3D glasses, obtains a health index of the user by using the biosignal information and controls a display state according to the health index. With this configuration, a user's health condition may be monitored in real-time with a biosignal of the user viewing a 3D image and a 3D display state may be controlled according to the user's health condition to thereby protect a user's health.

Abstract: Image processing is performed to facilitate subtractive crosstalk cancellation in 3D images. In a global embodiment, pixel values are compressed to provide sufficient foot room for subtractive crosstalk cancellation. For video images the degree of compression may vary from frame to frame. Temporal filtering may be applied to reduce flicker. In a local embodiment luminance is added to and/or compression is performed in local areas to facilitate more complete subtractive crosstalk cancellation. The amount or added luminance or compression may be matched to the requirements of the local areas. Added luminance and/or compression may be made to vary smoothly in time and smoothly in space. Displays and other apparatus may be constructed to perform methods for partial or complete crosstalk cancellation.

Abstract: A display device (1) includes: a light source (101) that outputs a laser beam; an illumination optical system (102) that emits illumination light of the laser beam; a diffraction pattern generation unit that generates a diffraction pattern from original image data; a spatial modulation element (103) that diffracts the illumination light by displaying the diffraction pattern; and a display control unit that performs at least one of a change in a display timing of a diffraction pattern the spatial modulation element (103) displays and a change in a size of a diffraction pattern the diffraction pattern generation unit generates.

Abstract: A three-dimensional display including a display and a micro-lens is provided. The display has a plurality of pixel units thereon, and each pixel unit has a pixel pitch i. The micro-lens is disposed at a side of the display, the micro-lens has a plurality of lens units thereon, and each lens unit has a lens pitch l. A right eye viewing zone and a left eye viewing zone are formed if an image displayed from the display passes though the micro-lens, wherein a distance between the center of the right eye viewing zone and the center of the left eye viewing zone is wz, and lens pitch l satisfies: 2 ? i > l ? 2 ? i × w z w z + i , wz is between 70 and 500 mm and i is between 0.1 and 500 ?m.

Abstract: A camera and camera system is provided with an optical device (8). The optical device creates simultaneously two or more images of object on a sensor (4) forming a compound image. The distance d between the constituting images of objects in the compound image is dependent on the distance Z to the camera. The compound image is analyzed (9), e.g. deconvolved to determine the distances d between the double images. These distances are then converted into a depth map (10).

Abstract: Methods and apparatuses are provided which may be implemented in various devices for to determine or assist in determining that a mobile station is at one or more particular indoor regions and to provide positioning assistance data and/or the like to the mobile station with regard to at least the one or more particular indoor regions.

Abstract: Endoscopic 3D data collection, including generating modulated measuring radiation, transmitting the measuring radiation to at least one partial area of a surface of an internal bodily cavity, receiving a signal radiation from the partial area of the surface of the cavity, transmitting the signal radiation from the distal to a proximal end portion of the shaft for reception by a time-of-flight (TOF) image sensor, and a controller to control the generation of the measuring radiation, to control the TOF image sensor and to evaluate the data supplied by the TOF image sensor to generate 3D data, also including a position sensor to record a position and an orientation of the shaft. The invention also relates to a method for endoscopic 3D data collection.

Abstract: In one aspect, a method is performed by one or more processors. The method includes receiving a primary view image showing a scene from a view of a primary camera; depth values for one or more objects in the scene; and a camera offset between the primary camera and a secondary camera. The method further includes determining disparities for each pixel in the primary view image. The method further includes generating a secondary view image using the primary view image, the depth values, and the camera offset. At least some of the pixels are repositioned according to the determined disparities.

Abstract: A method and apparatus for performing hybrid multihypothesis prediction during video coding of a coding unit includes: processing a plurality of sub-coding units in the coding unit; and performing disparity vector (DV) derivation when the coding unit is processed by a 3D or multi-view coding tool or performing block vector (BV) derivation when the coding unit is processed by intra picture block copy (IntraBC) mode. The step of performing DV or BV derivation includes deriving a plurality of vectors for multihypothesis motion-compensated prediction of a specific sub-coding unit from at least one other sub-coding/coding unit. The one other sub-coding/coding unit is coded before the corresponding DV or BV is derived for multihypothesis motion-compensated prediction of the specific sub-coding unit. A linear combination of a plurality of pixel values derived from the plurality of vectors is used as a predicted pixel value of the specific sub-coding unit.

Abstract: A 3D caption display method for harmoniously merging and displaying closed caption with 3D image in a 3D display apparatus, and a 3D display apparatus suitable for implementing the method. The 3D display apparatus receives a broadcast signal containing caption data, and obtains caption control commands including a 3D parameter setting command from the caption data. Afterwards, the 3D display apparatus displays a plurality of 3D caption images according to the caption control commands.

Abstract: To aim to achieve addition of blur to an image based on distance information of a subject and to appropriate determination of a block size that is a unit for coding. Blur is added to the image with use of one of disparity information for each pixel unit and distance information for each pixel unit and arbitrary blur conditions. A block size of each region of the image that are to be divided into blocks for coding is determined based on a blur value of the region. The image is divided into blocks based on the determined block sizes and coded in units of blocks. By increasing a block size with respect to a region included in an image having a high blur value, it is possible to reduce processing amount of reference block searching, thereby achieving speed-up of processing and reduction in processing amount.

Abstract: Embodiments of the invention generally relate to 3D stereo vision goggles or other platforms that could be used for enhanced vision systems for surgical applications, for patients with macular degeneration, or for entertainment or business applications. The invention takes images received from a video input source, and segments and projects those images off a mirror defined by a portion of an ellipsoid and directly onto the retina of the eye of a user. The invention allows users to enjoy 3D stereoscopic vision with an increased field of view, increased image quality, increased comfort, reduced cost, and other benefits.

Abstract: An image display apparatus and a method for controlling the same are provided. The method includes displaying at least one of a left-eye object or a right-eye object when the image display apparatus has entered a 3-dimensional (3D) mode, displaying a movement amount object indicating the amount of movement of pixel arrangement of the at least one of the left-eye object or the right-eye object, receiving a pixel arrangement movement amount input through the movement amount object, and changing at least one pixel of the displayed left-eye object to a pixel of the right-eye object and displaying the changed pixel or changing at least one pixel of the displayed right-eye object to a pixel of the left-eye object and displaying the changed pixel according to the pixel arrangement movement amount input. This increases user convenience when stereoscopic images are displayed in an autostereoscopic manner.

Abstract: To align a first digital 3D model of a scene with a second digital 3D model of the scene, real-world photographs of the scene are received and synthetic photographs of the first digital 3D model are generated according to different camera poses of a virtual camera. Using the real-world photographs and the synthetic photographs as input photographs, points in a coordinate system of the second digital 3D model are generated. Camera poses of the input photographs in the coordinate system of the second 3D model also are determined. Alignment data for aligning the first 3D model with the second 3D model is generated using the camera poses of the virtual camera and the camera poses corresponding to the input photographs.

Abstract: A method captures images of objects using an image capturing apparatus. The method obtains x-coordinate values, y-coordinate values, and z-coordinate values of the accelerations of a camera device sensed by a gravity sensor in a default time interval, calculates three-dimensional coordinate differences according to the obtained x-coordinate, y-coordinate, and z-coordinate values, and determines whether the three-dimensional coordinate differences are less than corresponding predefined thresholds. If at least one coordinate difference is not less than a corresponding predefined threshold, the method delays a period of time to obtain the x-coordinate, y-coordinate, and the z-coordinate values in a next default time interval. If all the three-dimensional coordinate differences are less than the corresponding predefined thresholds, the method controls the camera device to capture images of the subject object.

Abstract: A camera array, an imaging device and/or a method for capturing image that employ a plurality of imagers fabricated on a substrate is provided. Each imager includes a plurality of pixels. The plurality of imagers include a first imager having a first imaging characteristics and a second imager having a second imaging characteristics. The images generated by the plurality of imagers are processed to obtain an enhanced image compared to images captured by the imagers. Each imager may be associated with an optical element fabricated using a wafer level optics (WLO) technology.

Abstract: An image capture device includes: first and second shooting sections, each of which is configured to shoot an image of a subject; a disparity calculating section configured to generate a depth map based on first and second images that have been shot by the first and second shooting sections, respectively; and an image generating section configured to generate, based on the depth map and the first image, a third image that has as high a resolution as the first image and that forms part of a 3D image. The image generating section is controlled to determine whether or not to generate the third image based on at least one of the states of the first and second images, a zoom power during shooting, and the tilt of the image capture device during shooting.

Abstract: The present invention provides an image capturing technique for obtaining, at the same time, multiple images with parallax and an image that would cause no sensitivity problem even without mechanically operating any part of its image capturing system. The 3D image capture device of this invention includes: a light transmitting member 2 having a polarizing area A that transmits only a light ray polarized in a particular direction and a non-polarizing area C that transmits any light ray irrespective of its polarization direction; a solid-state image sensor 1 arranged to receive the light ray transmitted through the light transmitting member 2; an imaging section 3 for producing an image on the imaging area 1a of the solid-state image sensor 1; and an image generating section for generating images based on signals supplied from the image sensor 1, which includes a filter array including a polarization filter.

Abstract: A three dimensional (3D) video data processing method in a broadcast transmitter includes encoding, by an encoder, 3D video data which carries a first image and a second image in separate video streams; generating, by a system information processor, system information comprising 3D video composition information about the 3D video data; multiplexing, by a multiplexer, the system information and the 3D video data; and transmitting, by a transmitting unit, a broadcast signal carrying the 3D video data and the system information. The 3D video composition information includes first information on resolution of the 3D video data.

Abstract: An image processor 7 includes: an in-focus area extracting section 72 that extracts an in-focus area of two images with parallax; a color conversion matrix calculating section 73 that obtains a color conversion matrix between the two images by reference to information about the colors of pixels that are included in the in-focus area of the two images; and a color conversion section 74 that converts the color of one of the two images by using the color conversion matrix.

Abstract: An information processing apparatus includes a controller that sets type information, which represents that an application for executing a process using a dependent view video stream is an application for reproducing a 3-D image, in a clip information file which describes information on a transport stream including the dependent view video stream out of a base view video stream and the dependent view video stream obtained by encoding a plurality of video data according to the a predetermined video coding format.

Abstract: A 3D image capture device includes: a light transmitting member 2 with polarizing areas and a non-polarizing area; a solid-state image sensor 1 for receiving the light transmitted through the member 2; an imaging section 3 for producing an image on the imaging area 1a of the sensor 1; and an image generating section. The member 2 has n polarizing areas P(1), P(2), . . . and P(n) (where n is an integer and n?2), each of which transmits only a light ray polarized in a particular direction, and a non-polarizing area P(n+1) that transmits any light ray irrespective of its polarization direction. Those n polarizing areas have mutually different transmission axis directions. The sensor 1 includes a pixel array, divided into pixel blocks each consisting of (n+1) pixels, and a filter array including n polarization filters arranged so as to face n out of the (n+1) pixels and having different transmission axis directions.

Abstract: A measuring apparatus for measuring a stereo video format includes an active space measuring circuit and a decision circuit. The active space measuring circuit is utilized for determining a position of an active space of a frame packing to generate an active space measuring result according to pixels values of a plurality of scan lines of the frame packing. The decision circuit is coupled to the active space measuring circuit, and is utilized for determining the stereo video format according to at least the active space measuring result.

Abstract: 3D image data can be modified based on user preference data received from a user. The user preference data may be received at a first device and used to adjust 3D image data generated by the first device for presentation by a display device, or the first device may receive the user preference data and transmit it to a display device such that the display device may adjust the 3D image data based on the user preference data. The 3D image data may be adjusted based on user preference data to support presentation of 3D imagery on the display device in a manner desired by a user. 3D user viewing preferences may include an amount of pop-out effect in images, a stereo baseline of images, a depth range of images, a spatial distribution of images, a degree of depth sharpness in images, or specification of a user's dominant eye.

Abstract: Adjusting overlay positioning in stereoscopic video, including: receiving overlay data including a plurality of overlays, each overlay having a lateral axis value, a vertical axis value, and a depth value; receiving and displaying the stereoscopic video to a user as at least one of a video preview display and a stereoscopic display, each display including an overlay from the overlay data, wherein a position of the overlay in each display is based on the lateral axis value, the vertical axis value, and the depth value of the overlay, and wherein the video preview display includes interfaces for adjusting the position of the overlay in each display; receiving input from the user related to the depth value of the overlay; and adjusting the position of the overlay in the video preview display based on the input from the user.

Abstract: The present disclosure describes systems and methods for reducing ghosting in a three-dimensional (3-D) image system. According to embodiments of the present disclosure, a 3-D image generation system may comprise a first pixel disposed on a semiconductor element that emits light in a first color spectrum and a second pixel disposed on a semiconductor element that emits light in a second color spectrum. A controller may be coupled to the first pixel and the second pixel. The controller may cause the 3-D image generation system to display a first stereoscopic image using the first color spectrum and a second stereoscopic image using the second color spectrum. A filter may be coupled to at least one of the first pixel and the second pixel, and alter at least one of the first color spectrum and the second color spectrum.

Abstract: A method and apparatus are described including determining an inter-frame object displacement for each object in a left eye image frame pair, determining an inter-frame object displacement for each object in a right eye image frame pair, determining a convergence shifting field between each object in the left eye image and the right eye image pair, determining an amount of motion blur responsive to the inter-frame object displacement for each object in the left eye image frame pair, the inter-frame object displacement for each object in the right eye image frame pair, and the convergence shifting field between each object in the left eye image and the right eye image pair and adjusting the motion blur by the amount of motion blur.

Abstract: An apparatus for processing 3-Dimensional (3D) broadcast signals, comprises: a tuner for receiving broadcast signals containing 3D content; a service information processor for parsing target viewing information and at least one reference viewing condition information received from the broadcast signals which are received; a viewing analysis module for receiving viewing condition information of the viewer, parsing compensation-type information that is included in the reference viewing condition information, which contains information that is most relevant to the viewing condition information that is received, and for rendering the 3D content so that an element expressed by the correction-type information is maintained; and an output formatter for controlling so that the 3D content that is rendered is displayed.

Abstract: Disclosed herein is a display apparatus including: a display section; and a light-beam control section configured to control a light beam coming from the display section or a light beam propagating to the display section; the display apparatus having a first display mode for displaying a plurality of observing-point images on the display section wherein the observing-point images include two or more first observing-point images, and one or a plurality of second observing-point images, and the number of pixels included in each of the second observing-point images is smaller than the number of pixels included in each of the first observing-point images.

Abstract: A wireless signal transmission device of the present invention includes a wireless signal transmission section for, when an image display device displays a 3D image, (i) a sync signal indicative of timing at which a right-eye image and a left-eye image included in the 3D image are switched and (ii) an optical shutter control signal for controlling optical shutters of 3D image glasses which optical shutters alternately transmit and shut the right-eye image and the left-eye image, and for, when the image display device displays an image other than a 3D image, periodically transmitting a certain signal which does not include at least optical shutter control data.

Abstract: A liquid crystal display device (1) includes a liquid crystal panel having a plurality of pixels disposed in a matrix form, and a patterned retarder having retarder plates (RR) and retarder plates (RL) formed at positions corresponding to odd-numbered rows and even-numbered rows, respectively, of the liquid crystal panel. Among sub pixels disposed in the pixels positioned in the n-th row, a sub pixel electrode of a boundary-proximity sub pixel, which is positioned closest to a boundary between the associated retarder plate (RR) and the associated retarder plate (RL), is connected to an auxiliary bus line via a transistor having a gate electrode connected to a gate bus line in the (n?1)-th or prior row. In the second display mode, gate signals are sequentially supplied to the gate bus lines in order from the first to the N-th rows, and, in the first display mode, gate signals are sequentially supplied to the gate bus lines in order from the N-th to the first rows.

Abstract: Provided is an image processing apparatus and method thereof. The image processing apparatus may extract a three-dimensional (3D) bidirectional flow by analyzing data of an input object. The image processing apparatus may calculate a 3D volumetric center density of the input object based on the 3D bidirectional flow.

Abstract: An architecture has one or more systems for generating augmented reality environments configured to access cloud services over a network. A user is authenticated within the environments, and once authenticated is permitted to interact with the cloud services using the augmented reality environments as well as client resources provided within the environments. The client resources may include devices or things that are primary intended for use within the environments, and devices or things that are not typically associated with augmented reality environments. The architecture enables the client resources to function as thin client interfaces to the cloud services.

Abstract: Autostereoscopic display. The display includes an array of elements from which light emanates, the elements being rotatable about two orthogonal axes by microcontrollers. An eye tracker is provided for determining the location in three dimensions of at least one eye viewing the array. The microcontrollers, using information from the eye tracker, rotate the elements to mimic a concave surface to deliver light to the eye. It is preferred that the elements are mirrors and the display further includes a projector for projecting an image on the array for reflection to the eye. The elements themselves may include structure for generating light rather than reflecting light.

Abstract: To enhance the accuracy of the search of a corresponding point in a plurality of sheets of images photographed by a camera array and to acquire more pieces of color information on a subject. First color information is calculated from pixel values of the plurality of pieces of photographed image data photographed by the camera array, and the first color information is used to calculate a corresponding point between images indicated by the plurality of pieces of photographed image data. The calculated corresponding point is used to calculate information on the depth of the subject in the image indicated by the photographed image data. Second color information that is used for reproducing the color of the subject faithfully is calculated from the pixel values of the plurality of pieces of photographed image data. The calculated depth information and second color information are used to combine the plurality of photographed images.

Abstract: The stereo display apparatus displays parallax images to present a stereo image. The apparatus acquires the parallax images and information on a maximum pixel shift amount and a minimum pixel shift amount of the parallax images, calculates maximum and minimum relative parallax amounts corresponding to the maximum and minimum relative parallax amounts, by using the information on the maximum and minimum pixel shift amounts and a display condition, and determines whether or not at least one of the maximum and minimum relative parallax amounts exceeds a fusional limit criterion value. The apparatus determines whether or not a difference between the maximum and minimum relative parallax amounts exceeds a fusional limit range amount if the at least one of the maximum and minimum relative parallax amounts exceeds the fusional limit criterion value.

Abstract: An image display apparatus and a method for operating the same are disclosed. The method for operating an image display apparatus includes receiving a three-dimensional (3D) image, calculating an Average Picture Level (APL) of the 3D image, and changing of a depth of the 3D image according to the calculated APL.

Abstract: Disclosed herein is an information processing apparatus, including: an acquisition section adapted to acquire stereoscopic image information for displaying a stereoscopic image; and a production section adapted to compare a first image and a second image, which configure the acquired stereoscopic image information, with each other to produce a parameter indicative of a position of a body included in the stereoscopic image in the depthwise direction when the stereoscopic image is displayed.

Abstract: A method of using a computer to generate virtual autostereoscopic images from a three-dimensional digital data set is disclosed. The method includes establishing a first point of view and field of view of a subject volume including a region of interest. The method includes reading at least one scene parameter associated with the field of view of the subject volume. The method includes determining a second point of view offset some distance and along some vector from the first point of view based on a value derived from at least one scene parameter. The second point of view at least partially overlaps the first field of view. The first and second points of view each create a view plane with a view orthogonal to the subject volume.

Abstract: A video signal processing device processes a 3D video signal including a left-eye image and a right-eye image. The video signal processing device includes an OSD control unit generating a left-eye superimposition image and a right-eye superimposition image, an OSD superimposing unit superimposing the left-eye superimposition image on the left-eye image and the right-eye superimposition image on the right-eye image, so as to generate an output image, and a video output unit providing the output image. The OSD control unit includes a first register holding a left-eye parameter for generating the left-eye superimposition image, and a second register holding a right-eye parameter for generating the right-eye superimposition image. The OSD control unit generates the left-eye superimposition image and the right-eye superimposition image by shifting positions of pixels in a predetermined image based on the left-eye parameter and the right-eye parameter.

Abstract: A method for automatically detecting and tracking multiple targets in a multi-camera surveillance zone and system thereof. In each camera view of the system only a simple object detection algorithm is needed. The detection results from multiple cameras are fused into a posterior distribution, named TDP, based on the Bayesian rule. This TDP distribution represents a likelihood of presence of some moving targets on the ground plane. To properly handle the tracking of multiple moving targets with time, a sample-based framework which combines Markov Chain Monte Carlo (MCMC), Sequential Monte Carlo (SMC), and Mean-Shift Clustering, is provided. The detection and tracking accuracy is evaluated by both synthesized videos and real videos. The experimental results show that this method and system can accurately track a varying number of targets.

Abstract: A method for controlling an image display apparatus includes determining a type of a video signal included in an input signal, determining whether three-dimensional (3D) format information is included in the input signal, if the video signal is a 3D video signal, requesting 3D format information about the video signal to a server that stores 3D format information, if the input signal does not include the 3D format information about the video signal, and processing, upon receipt of 3D format information from the server in response to the 3D format information request, the video signal according to the 3D format information and displaying a 3D image based on the processed video signal.

Abstract: A playback method of a multimedia content includes: receiving the multimedia content; performing playback upon the multimedia content; detecting a user status and accordingly generating a detection result; and adjusting the playback of the multimedia content when the detection result indicates a change of the user status. A playback apparatus of a multimedia content includes a receiving block, a playback block, and a detecting block. The receiving block is used for receiving the multimedia content. The playback block is coupled to the receiving block, and used for performing playback upon the multimedia content. The detecting block is coupled to the playback block, and used for detecting a user status and accordingly generating a detection result. The playback block adjusts the playback of the multimedia content when the detection result indicates a change of the user status.

Abstract: There are provided a transmitter, a display, a shutter eyeglass device, a transmission/reception system, a display system and a transmission/reception method allowed to achieve highly reliable communication between a transmission side and a reception side. The transmitter includes: a transmission section holding plural kinds of commands each represented by a plurality of bits and repeatedly transmitting a command set, the command set being configured of one or more kinds of commands which are selected from the plural kinds of commands and combined in predetermined order, in which a bit pattern representing a whole of the command set is the same as a bit pattern held in a receiver.

Abstract: A display control program executed on a computer of a display having a first display portion capable of providing stereoscopic display and a second display portion configured to provide two-dimensional display is provided. The display control program includes object display instructions for controlling the first display portion and the second display portion such that a plurality of objects are displayed at respective arrangement positions set by arrangement position setting instructions and an object group is displayed across the first display portion and the second display portion. The object display instructions include instructions for determining on which of the first and second display portions objects included in the object group are to be displayed, and for providing stereoscopic display of an object determined to be displayed on the first display portion and providing two-dimensional display of an object determined to be displayed on the second display portion.

Abstract: The invention provides a complete system for three-dimensional (3D) (stereo) still photography in a digital format. This includes capturing the image or photo, viewing, printing and projecting it. Intermediate steps would include downloading images to a computer, editing, enhancing or modifying, saving, recording photo images to other storage medium, and the printing of still photos. This invention is a significant advancement of the traditional analog film stereo slides, in that the digital format will allow viewing of the image in the camera in 3D, prior to, during, immediately after exposure and at any other time after exposure. With significant computer processing capability after exposure in editing, enhancing, color correcting, adding text and art, the images are further improved. The system includes the ability to view images, in 3D (stereo), in the camera, in a hand held viewer, on a computer screen on a standard television set as well as printed pairs or in anaglyph formats.

Abstract: A method for depth mapping includes providing depth mapping resources including an illumination module, which is configured to project patterned optical radiation into a volume of interest containing the object, and an image capture module, which is configured to capture an image of the pattern reflected from the object. A depth map of the object is generated using the resources while applying at least one of the resources non-uniformly over the volume of interest.

Abstract: In some embodiments, a method of rendering a stereoscopic image based on a two-dimensional image frame and a depth map comprises generating a saliency map of the two-dimensional image frame, determining a region where is located an object of focus from the saliency map, modifying the depth map such that a range of depth values in the depth map that is associated the object of focus is redistributed toward a depth level of a display screen, and generating a virtual stereoscopic image frame based on the modified depth map and the two-dimensional image frame. In other embodiments, systems of rendering stereoscopic images are also described.