Samsung Electronics Co., Ltd.

Snu Rdb Foundation

Aarhus Universitet

In Woo Ha

Min Su Ahn

Dong Kyung Nam

Jin Ho Lee

Hyong Euk Lee

Do Kyoon Kim

Ju Yong Park

Tae Hyun Rhee

Yong Beom Lee

Kyu Young Hwang

Sung H Hong

Jongmin Kim

Kee Chang Lee

Minsu Ahn

Jeong Hwan Ahn

Na Hyup Kang

Seo Young Choi

Jehee Lee

Jacob Toft Pedersen

Toshiya Hachisuka

Seung In Park

Hyoung Euk Lee

Myung Jin Eom

Min-su Ahn

Dong Kyung Park

Disclosed is a method and apparatus for three-dimensional (3D) rendering, the apparatus including a processor configured to extract shading information, visibility information and shape information from a region of an input image, determine a light source based on the shading information, the visibility information, and the shape information of the region, and generate a 3D rendering image by rendering the input image based on the determined light source.

Method and apparatus for three-dimensional (3D) rendering

An image processing apparatus and method are provided. The image processing method may generate a mask for preventing a virtual light source from being sampled on an area of a current image frame based on virtual light source information of a previous image frame, applying the mask to the current image frame, sampling the virtual light source in the current image frame to which the mask is applied, and rendering the current image frame based on the virtual light source sampled in the current image frame.

Method and apparatus for processing image

An image processing apparatus to calculate a visibility with respect to a plurality of virtual point lights (VPL) sampled at a three-dimensional (3D) model includes at least one first VPL included in a screen scene associated with a viewpoint to render and at least one second VPL not found in the screen scene, and may calculate a first probability obtained by calculating a visibility between a first area including the first VPL and a first point with respect to the at least one first VPL.

Apparatus and method for processing virtual point lights in an image

Image processing apparatus and method. A modeling unit may generate a three-dimensional (3D) model corresponding to an actual object from an input color image and an input depth image corresponding to the input color image. A calculator may perform photon-based rendering with respect to an input virtual object and the 3D model based on input light environment information, and may generate a difference image comprising color distortion information occurring by inserting the virtual object into the 3D model. A rendering unit may generate a result image comprising the virtual object by synthesizing the difference image and the input color image.

Apparatus and method for image processing

A generator of an image processing apparatus may generate a light transport map (LTM) by sampling depth information from a light to an object based on a transparency of the object, wherein the LTM may be used to compute a visibility of the light with respect to a first point to be rendered.

Apparatus and method for generation of a light transport map with transparency information

A sampler of an image processing apparatus may sample at least one first virtual point light (VPL) from a direct light view. The sampler may sample a second VPL in a three-dimensional (3D) space independent of the direct light view. A calculator may calculate a luminance of the second VPL using a first VPL adjacent to the second VPL selected from among the at least one first VPL.

Image processing apparatus and method using virtual point light (VPL) information

An image processing apparatus may include a light capturing unit to generate light environment information by photographing or capturing a light environment of an object, and an object capturing unit to generate object information by photographing or capturing the object. The image processing apparatus may further include a modeling unit to generate a 3-dimensional (3D) model by reflecting or combining the light environment information and the object information, and a rendering unit to render a resultant image with respect to at least one view using the 3D model.

Image processing apparatus and method

Provided is an image processing apparatus for performing photon mapping, and the image processing apparatus may perform ray tracing for photon mapping, sample a ray space based on a result of the ray tracing, and perform pseudo photon mapping using the sampled ray space.

Image processing apparatus and method using photon mapping and ray tracing and increasing a rate of photon mapping

An apparatus and method for forming a light field image includes projecting vertices of a graphic object to a far plane corresponding to a first distance directed to a screen reproducing a light field, and forming the light field image with respect to the graphic object using the vertices projected to the far plane.

Apparatus and method for forming light field image

An image processing apparatus. The image processing apparatus may perform filtering to emphasize a surface lighting of a low frequency band from an input lighting environment image, and may also perform at least one virtual point light (VPL) sampling from the input lighting environment image. The image processing apparatus may perform precomputed radiance transfer (PRT) based rendering using the filtered lighting environment image and VPL based rendering using the sampled VPL.

An image processing apparatus may include a storage unit to store a lookup table (LUT) including information on corresponding relations between an occlusion vector related to at least one point of a 3-dimensional (3D) object and a spherical harmonics (SH) coefficient; and a rendering unit to determine a first SH coefficient corresponding to a first occlusion vector related to a first point of the 3D object using the LUT and to determine a pixel value of the first point using the first SH coefficient.

Image processing apparatus and method utilizing a lookup table and spherical harmonic coefficients

A display apparatus that may generate a high density light field image is provided. The display apparatus may identify an eye position of a user and set a virtual viewing window around the eye of the user. The display apparatus may generate a directional light corresponding to the viewing window and generate a high density light field image.

Display apparatus and method

A three dimensional (3D) image processing using ray tracing. The 3D image processing includes checking for a collision of rays, each ray respectively corresponding to a pixel of a plurality of pixels included in an image, and generating a plurality of corresponding ray trees to a first depth; and checking a collision of rays, each ray respectively corresponding to at least one pixel of the plurality of pixels, and updating a ray tree corresponding to the at least one pixel to a second depth.

Hierarchical based 3D image processor, method, and medium

Provided is a data processing apparatus that may include a storage unit, a first calculator, and a second calculator. The storage unit may store a plurality of training data obtained by motion sensing. The first calculator may calculate a first transformation matrix by performing a regression analysis for the plurality of training data. The second calculator may calculate first output data by applying the first transformation matrix to first input data.

Data processing apparatus generating motion of 3D model and method

An image processing apparatus is provided. The image processing apparatus may include a first calculator to generate a first shadow map with respect to a static object included in a three-dimensional (3D) model, at a first viewpoint within the 3D model, a second calculator to generate a second shadow map with respect to a dynamic object included in the 3D model, at the first viewpoint, and a third calculator to generate a third shadow map with respect to the 3D model at the first viewpoint by synthesizing the first shadow map and the second shadow map. The image processing apparatus may decrease an amount of calculation necessary when performing three-dimensional (3D) rendering for a plurality of frames.

Growing community of inventors

Yongin-si, South Korea

In Woo Ha