30 results about "Non-photorealistic rendering" patented technology

The invention relates to non-photorealistic rendering in computer graphics, in particular to digital simulation and synthesis with artistic style of Yunnan heavy-color painting, and belongs to the technical field of non-photorealistic graphic rendering. The digital simulation and synthesis are characterized in that: the digital simulation and synthesis comprise an establishment and management module of a Yunnan heavy-color painting basic graphic element library, a graphic element library-based Yunnan heavy-color painting traditional delineation drawing rendering module, and a Yunnan heavy-color painting traditional delineation drawing-based coloring and rendering module. The basic graphic element library is used for providing graphic elements needed by foreground traditional delineation drawings, such as hair, facial forms, trunks and the like. The Yunnan heavy-color painting traditional delineation drawing rendering module can select appropriate graphic elements from the graphic element library to combine the graphic elements by layers so as to generate the Yunnan heavy-color painting traditional delineation drawings. In order to harmoniously collocate all the graphic elements, a system provides multiple kinds of operation for the graphic elements, such as translation, selection, scaling and the like and can modify the shapes of the graphic elements at the same time. The Yunnan heavy-color painting traditional delineation drawing-based coloring and rendering module is in charge of coloring the traditional delineation drawings, and the effects of coloring can reflect texture characteristics and color characteristics in an original drawing of the heavy-color painting, and special characteristic simulation of the Yunnan heavy-color painting, such as character edge hollow sense, background fusion and the like is realized.

The invention relates to an interactive video stylized rendering method based on video interpretation, wherein an interactive video semantic segmentation module and a video stylization module are utilized. A segmentation method of the interactive video semantic segmentation module comprises the following steps of: (1) interactive segmentation and automatic identification of key frame images; (2) matching of dense characteristic points among key frames; and (3) area competition segmentation. A stylization method of the video stylization module comprises the following steps of: (4) un-reality sense drawing of the key frames based on semantic analysis; (5) a brushwork propagating method of a sequence frame; and (6) a damping pen brush system for preventing shaking. The interactive video stylized rendering method based on the video interpretation, disclosed by the invention, has the advantages of short manufacturing period, low cost and favorability on manufacturing in batches.

The invention discloses a linear feature extracting method for three-dimensional point cloud. The linear feature extracting method for the three-dimensional point cloud includes the following steps: S1, projecting an original point cloud to a two-dimensional space along different directions to generate a plurality of two-dimensional images, keeping the depth information, using a non-photorealistic rendering technology to convert the depth information into an image grey value, and enabling each two-dimensional image to have clear edges; S2, extracting a two-dimensional linear support area from the two-dimensional image; S3, projecting the two-dimensional linear support area to the three-dimensional space to obtain a three-dimensional linear support area. By means of projection and back projection, the extraction for the three-dimensional linear support area is converted into the extraction for the two-dimensional linear support area, the data processing complexity is lowered, and linear features can be quickly and precisely extracted from large amount of point cloud data.

A method and system for rendering a captured image of a scene is disclosed which provide see-through vision through the rendered image, for example of an augmented reality object rendered behind the scene, by assigning pixel transparency values in dependence upon captured image pixels. The method and system preserve some structure of the scene in the rendered image without requiring a model of the scene.

The invention provides a visualization method for multilayer shape feature fusion on a GPU (Graphics Processing Unit). According to the method, the sequencing and collecting of multiple fragments can be conducted by adopting a multilevel depth test strategy-based improved k-buffer algorithm, the multi-fragment stylized rendering technology can be formed by performing geometrical feature extraction on the multilayer fragments and combining a non-photorealistic rendering method, so that the shape features of multilayer geometrical surfaces in the front and the back and the middle of a single model or multiple models in a large-scale scene can be shown. Through the shape feature on the multilayer surfaces of the model, not only can the stylized rendering effect of various transparent and semi-transparent objects be shown, but also a user can conveniently observe the surface structure feature of the model. A good stylized feature visualization effect can be realized only by geometrically drawing a model scene in the GPU twice, and the real-time rate can be achieved.

The invention relates to a manufacturing method of a shadow figure model based on a common three-dimensional model. A common three-dimensional model is used as an input material, and the techniques of model cutting (gridding division), three-dimensional model transferring into two-dimension, secondary editing of shadow figure components, generating of a shadow figure component model, assembling of shadow figure model components and the like are used to manufacture shadow figure models. The manufacturing method can effectively stylize the common three-dimensional models into shadow figure models with traditional shadow figure aesthetic features. Current three-dimensional shadow figure model manufacture only can be completed by using professional modeling tools of 3DMAX and the like to start step by step from the very beginning, and is not only time-consuming but also has high professional requirement to manufacturing staff. The manufacturing method of the shadow figure model based on the common three-dimensional model can stylize the existing common models from a non-photorealistic drawing angle, provides an interactive operation, and is simple in manufacture process, shadow figure model images are vivid, and the professional requirements to producing staff are reduced. Meanwhile a material source is wide, and the application range of the manufacturing method of the shadow figure model based on the common three-dimensional model is broadened.

A method and system for rendering a captured image of a scene is disclosed which provide see-through vision through the rendered image, for example of an augmented reality object rendered behind the scene, by assigning pixel transparency values in dependence upon captured image pixels. The method and system preserve some structure of the scene in the rendered image without requiring a model of the scene.

The invention discloses a method for rendering character animation in an artistic manner with the assistance of a computer. The method is based on an illumination spherical model. The invention is characterized in that the illumination spherical model which extracts and creates an artistic style from a work of art is applied to rendering of a character model, so that coloring of an artistic style is realized conveniently and rapidly, and character animation can be manufactured as if by non-photorealistic rendering. By drawing on a method for rendering information about illumination on a sphere, the invention ensures that when a complex object which is uniform in illumination material is rendered, the illumination is consistent in an all-round manner. Because of extraction and application of the illumination spherical model, character rendering of the artistic style can be realized conveniently and rapidly only through simple interactive operation, so that rendering efficiency is improved. The invention solves the problems that the prior computer assisted animation has low rendering efficiency, and the traditional image technology cannot give expression to works of an artist flexibly.

The invention discloses a mobile terminal based image processing method, which comprises that: a user determines an image to be processed; the mobile terminal acquires non-photorealistic rendering (NPR) processing parameters of the image to be processed; and the mobile terminal carries out NPR processing on the image to be processed according to the acquired NPR processing parameters. The invention correspondingly discloses the mobile terminal, which comprises a central processing module and an NPR processing module. By processing the image through NPR technology, the diversification and individuation of the image can be realized so as to meet the requirement of the user on the individuation of the image; in addition, the simplified image is transmitted, the transmitted image data are reduced, so the image transmission speed can be improved and the bandwidth can be saved so as to improve user experience.

The invention relates to a volume data non-photorealistic rendering method based on GPU (graphic processing unit) acceleration. The method comprises the following steps of carrying out the direct volume rendering for medical volume data under multiple viewpoints, acquiring a plurality of rendering results, extracting a characteristic line for the two-dimensional rendering result, defining a global energy miniaturization rule, calculating a three-dimensional characteristic line, utilizing a convolution surface method to define a scalar field, clustering the three-dimensional characteristic line, utilizing a B-type curve to fit the line, and completing the stylized rendering. By utilizing the powerful calculation capacity of the GPU, the rendering speed and efficiency can be greatly improved.

The application discloses an image non-photorealistic rendering method and system. The method includes the following steps: extracting a region of interest in a source image; carrying out watershed transformation on the region of interest, and segmenting the region-of-interest image into multiple sub regions; processing each sub region through a mean shift algorithm, and filling the processed subregions with color; and fusing the colored sub regions and smoothing the edges to get a non-photorealistic rendered image. In the application, through the introduction of a region-of-interest extracting technology to image analysis, the redundant information of the image is eliminated to a certain extent, the primary content of the image is highlighted, the interference brought by secondary content is eliminated, the image NPR time efficiency algorithm is improved, and a non-photorealistic artistic image of a water color style is realized. Moreover, manual intervention in the processing process is reduced as much as possible, and a friendly user interface is provided.

A method for generating two-dimensional image space noise. The method includes receiving a first frame of a rendered animation sequence; receiving a second frame of the rendered animation sequence; and generating a frame of noise that is associated with at least one object moving between the first frame and the second frame and is to be applied to the second frame, where generating the frame of noise comprises applying, for each pixel in the second frame, a causal filter based on a depth associated with the pixel and a velocity associated with the pixel.

The invention provides a method for simulating a solid combustion process based on a thermodynamic model. The method comprises the following four steps of: a pre-calculation stage which is used for treating changes of details such as geometrical information of the model surface and the texture color of the model after combusted; a stage of flame diffusion calculation of the object surface, which is used for calculating the combustion range of the flame on the model surface at the next time by using thermodynamic model iteration according to the combustion state of the current model; a stage of deformation calculation of a flame object, which is used for calculating the deformation calculation degree of the model by combining the material characteristic of the model surface according to the flame diffusion range and the combustion state; and a non-photorealistic rendering stage, which is used for implementing the non-photorealistic rendering for the flame and the model according to the combustion state of the object in a virtual scene. The method provided by the invention can be used for simulating the flame diffusion on the object surface in the combustion process based on a GPU (Ground Power Unit) and simulating the deformation calculation process of the object due to the combustion, can also be used for implementing the realistic rendering for the flame, and has the characteristics of good real-time performance and strong physical realism.

The invention relates to a texture synthesis method based on controllable pyramid decomposition. The method is characterized in that: reading an object image in matlab software, and generating an initial image with random and uniform distribution of gray scale; carrying out histogram coupling on the initial image and an object image; carrying out pyramid decomposition on the object image and a random image respectively, carrying out the histogram coupling on each corresponding sub-band which is decomposed, followed by storing in a pyramid data structure after coupling, and carrying out inverse transformation reconstruction to obtain a new image; and finally carrying out continuous cycle operation to obtain an image whose texture direction is similar to that of the object image. By employing the method, a synthetic image has a clear texture, and an effect is good. Simultaneously, operation is simple, speed is fast, and the method has wide application prospect in aspects of image editing, data compression, rapid transmission of network data, generation of a large scale scene, photorealistic rendering and non-photorealistic rendering and the like.

There are provided a unified framework based on extensible styles for 3D non-photorealistic rendering and a method of configuring the framework. The unified framework includes: 3D model data processing means for generating a scene graph by converting a 3D model input into 3D data and organizing the scene graph using vertexes, faces, and edges; face painting means for selecting a brusher to paint faces (interiors) of the 3D model using the scene graph; line drawing means for extracting line information from the 3D model using the scene graph and managing the extracted line information; style expressing means for generating a rendering style for the 3D model and storing the rendering style as a stroke, the rendering style being equally applied to a face-painting method and a line-drawing method; and rendering means for combining the stroke and the selected brusher to render the 3D model using both the face-painting method and the line-drawing method. The framework can be used to develop tools and new rendering styles for non-photorealistic rendering and animation.

A method for rendering a non-photorealistic (NPR) content from a set (SI) of at least one image of a same scene is provided. The set of images (SI) is associated with a depth image comprising a set of regions. Each region corresponds to a region of a given depth. The method for rendering a non-photorealistic content includes generation (21) of a segmented image having at least one segmented region generated with a given segmentation scale, wherein the at least one segmented region corresponds to at least one region of the set of regions; generation of a binary edge image in which at least one binary edge region is generated with a given edge extraction scale, the at least one binary edge region corresponding to at least one region of the set of regions; and rendering (23) of the non-photorealistic content by combining the segmented image and the binary edge image.

A display apparatus and a Non-Photorealistic Rendering process (NPR) are provided. The display apparatus includes: an image processor which processes an NPR with respect to an image so that brightness of a pixel having a brightness value less than a predetermined brightness value is reduced and a brightness of a pixel having a brightness value greater than the predetermined brightness value is increased. Accordingly, a cartoon effect can be maximized.

The invention discloses a water color style non-photorealistic rendering method and device, and belongs to the field of image processing. The water color style non-photorealistic rendering method includes the steps of obtaining an image c by extracting the outline of an image, meanwhile, converting the image into an image f of an HIS space from an RGB space, then removing I components in the image f, enabling a corresponding point pixel value in the image c to be multiplied by a specific coefficient to serve as an I component value of the corresponding pixel in the image f to form a new image g, and then converting the image g from an HSI space to the RGB space to obtain an image b. According to the water color style non-photorealistic rendering method, the water color style of the image can be achieved, the high simulated effect is achieved, the color is bright and limpid, the line outline is clear, the calculating speed is high, and real-time implementation can be achieved.

The invention relates to non-photorealistic rendering in computer graphics, in particular to digital simulation and synthesis with artistic style of Yunnan heavy-color painting, and belongs to the technical field of non-photorealistic graphic rendering. The digital simulation and synthesis are characterized in that: the digital simulation and synthesis comprise an establishment and management module of a Yunnan heavy-color painting basic graphic element library, a graphic element library-based Yunnan heavy-color painting traditional delineation drawing rendering module, and a Yunnan heavy-color painting traditional delineation drawing-based coloring and rendering module. The basic graphic element library is used for providing graphic elements needed by foreground traditional delineation drawings, such as hair, facial forms, trunks and the like. The Yunnan heavy-color painting traditional delineation drawing rendering module can select appropriate graphic elements from the graphic element library to combine the graphic elements by layers so as to generate the Yunnan heavy-color painting traditional delineation drawings. In order to harmoniously collocate all the graphic elements, a system provides multiple kinds of operation for the graphic elements, such as translation, selection, scaling and the like and can modify the shapes of the graphic elements at the same time. The Yunnan heavy-color painting traditional delineation drawing-based coloring and rendering module is in charge of coloring the traditional delineation drawings, and the effects of coloring can reflect texture characteristics and color characteristics in an original drawing of the heavy-color painting, and special characteristic simulation of the Yunnan heavy-color painting, such as character edge hollow sense, background fusion and the like is realized.

The invention relates to a volume data non-photorealistic rendering method based on GPU (graphic processing unit) acceleration. The method comprises the following steps of carrying out the direct volume rendering for medical volume data under multiple viewpoints, acquiring a plurality of rendering results, extracting a characteristic line for the two-dimensional rendering result, defining a global energy miniaturization rule, calculating a three-dimensional characteristic line, utilizing a convolution surface method to define a scalar field, clustering the three-dimensional characteristic line, utilizing a B-type curve to fit the line, and completing the stylized rendering. By utilizing the powerful calculation capacity of the GPU, the rendering speed and efficiency can be greatly improved.

The present invention provides an image non-photorealistic rendering method and device. The device comprises a to-be-processed image obtaining module, a decoloration processing module, a first Gauss fuzzy processing module, a first image merging module, a second Gauss fuzzy processing module and a second image merging module. The method of the present invention improves greatly on the basis of a conventional rendering method, obtains the new image values by the pixel mathematical calculation, can obtain the images of a similar ink stained form directly, at the same time, can sketch the valuable form edges very clearly, can save a lot of work for the post processing fabricators, enables the subjective image forms to approach the freehand sketching better, and does not have the gradient and stray point phenomena.

The invention relates to a non-photorealistic rendering method for a three-dimensional network model with stylized typical lines, which comprises the following main steps: 1) calculating the principal direction and the principal curvature of each vertex in a three-dimensional network model; 2) solving the radial curvature of each vertex in the three-dimensional network model under the current viewpoint position, and normalizing all the radial curvatures; 3) carrying out cartoon rendering on the three-dimensional network model by using two-dimensional cartoon textures based on the normalized radial curvatures; 4) extracting typical lines of the three-dimensional network model, and expanding the typical lines along the normal directions of the vertices of the three-dimensional network modelto form a quadrangle; and 5) carrying out texture mapping on the typical lines of the three-dimensional network model by using two-dimensional stylized textures to generate the stylized rendering effect of the typical lines. Based on the above steps, the invention realizes the non-photorealistic rendering of the three-dimensional network model with stylized typical lines.

The invention relates to the field of computer graphics, real-time non-photorealistic rendering and plant behavior simulation combination technology, and discloses a material model-based method for simulating the appearance change of plant leaves. The method comprises the following steps: S1, dividing the plant leaf into a four-layer structure including an epidermis layer, a palisade tissue layer, a spongy tissue layer and a hypodermis layer; S2, aiming at the four-layer structure, constructing a material model based on a plant leaf physiology factor; S3, simulating the spatial difference phenomenon of the plant leaf by regulating the pigment distribution of the leaf; and S4, simulating the temporal appearance change phenomenon of the plant leaf by regulating the pigment change rate. Modeling is conducted by fully considering that the action of physiology factors of the leaf structure and pigment and the like influencing the leaf appearance to the material of the leaf, so that not only can the modeling on spatially heterogeneous leaf reflection and transmission appearance characteristics be realized, but also simulation on the space change and time change characteristics can be conducted.

The present invention discloses an image non-photorealistic highlight water color rendering method and apparatus. According to the method disclosed by the present invention, by firstly carrying out equalization processing on an input image, light in the image is balanced; normalization processing is carried out to bring convenience to subsequent calculation; and then line collection processing is carried out on the original color image by a gray-scale map of the image so as to extract a necessary edge profile, the extracted edge and the original color image are merged into a new image and finally, enhancement processing is carried out on the new image and the color of the image is corrected. According to the method disclosed by the present invention, the necessary edge can be enhanced, the image is excellent in edge layering, is insensitive to light influence and has a good artistic feeling, no excessive color particles exist, the highlight rendering method is provided for the art and the non-photorealistic rendering processing, such as filtering processing and the like, and video real-time implementation can be met.

The invention relates to a manufacturing method of a shadow figure model based on a common three-dimensional model. A common three-dimensional model is used as an input material, and the techniques of model cutting (gridding division), three-dimensional model transferring into two-dimension, secondary editing of shadow figure components, generating of a shadow figure component model, assembling of shadow figure model components and the like are used to manufacture shadow figure models. The manufacturing method can effectively stylize the common three-dimensional models into shadow figure models with traditional shadow figure aesthetic features. Current three-dimensional shadow figure model manufacture only can be completed by using professional modeling tools of 3DMAX and the like to start step by step from the very beginning, and is not only time-consuming but also has high professional requirement to manufacturing staff. The manufacturing method of the shadow figure model based on the common three-dimensional model can stylize the existing common models from a non-photorealistic drawing angle, provides an interactive operation, and is simple in manufacture process, shadow figure model images are vivid, and the professional requirements to producing staff are reduced. Meanwhile a material source is wide, and the application range of the manufacturing method of the shadow figure model based on the common three-dimensional model is broadened.