Showing papers on "Alpha compositing published in 2007"

Efficient gradient-domain compositing using quadtrees

Abstract: We describe a hierarchical approach to improving the efficiency of gradient-domain compositing, a technique that constructs seamless composites by combining the gradients of images into a vector field that is then integrated to form a composite. While gradient-domain compositing is powerful and widely used, it suffers from poor scalability. Computing an n pixel composite requires solving a linear system with n variables; solving such a large system quickly overwhelms the main memory of a standard computer when performed for multi-megapixel composites, which are common in practice. In this paper we show how to perform gradient-domain compositing approximately by solving an O(p) linear system, where p is the total length of the seams between image regions in the composite; for typical cases, p is O(√n). We achieve this reduction by transforming the problem into a space where much of the solution is smooth, and then utilize the pattern of this smoothness to adaptively subdivide the problem domain using quadtrees. We demonstrate the merits of our approach by performing panoramic stitching and image region copy-and-paste in significantly reduced time and memory while achieving visually identical results.

Simultaneous Matting and Compositing

Abstract: Recent work in matting, hole filling, and compositing allows image elements to be mixed in a new composite image. Previous algorithms for matting foreground elements have assumed that the new background for compositing is unknown. We show that, if the new background is known, the matting algorithm has more freedom to create a successful matte by simultaneously optimizing the matting and compositing operations. We propose a new algorithm, that integrates matting and compositing into a single optimization process. The system is able to compose foreground elements onto a new background more efficiently and with less artifacts compared with previous approaches. In our examples, we show how one can enlarge the foreground while maintaining the wide angle view of the background. We also demonstrate composing a foreground element on top of similar backgrounds to help remove unwanted portions of the background or to re-scale or re-arrange the composite. We compare and contrast our method with a number of previous matting and compositing systems.

A Matte-less, Variational Approach to Automatic Scene Compositing

Abstract: In this paper, we consider the problem of compositing a scene from multiple images. Multiple images, for example, can be obtained by varying the exposure of the camera, by changing the object at focus, or by simply sampling a video sequence at arbitrary time instants. We develop this problem in an optimization framework and then adopt a variational approach to derive a generalized algorithm which will be able to solve diverse applications depending on the nature of the input images. Our approach has distinct advantages over the existing digital compositing techniques, such as alpha matting and alpha blending, which require an explicit preparation of the matte while there is no such requirement in the proposed technique. We demonstrate the usefulness of our approach through results from diverse applications in computer vision.

Gradient-domain compositing

Abstract: Systems, methods, and apparatus, including computer program products, for forming composite images using gradient-domain compositing are provided. In some implementations, a method is provided. The method includes receiving two or more source images and aligning the received source images to form an assembled composite image. The method also includes stitching the seams between the aligned source images in the assembled composite image to form a final composite image. The stitching includes performing a gradient domain compositing. The gradient domain compositing uses a subset of pixels in the assembled composite image including calculating individual pixel values along the seams and interpolating pixel values away from the seams.

Soft edge smoothness prior and application on alpha channel super resolution

Abstract: Systems and methods are disclosed for processing a low resolution image by performing a high resolution edge segment extraction on the low resolution image; performing an image super resolution on each edge segment; performing reconstruction constraint reinforcement; and generating a high quality image from the low quality image.

System and method of treating semi-transparent features in the conversion of two-dimensional images to three-dimensional images

Abstract: A two dimensional image which has a semitransparent object in the foreground of the image has three contributions to the final color shown in a pixel where the semitransparent object is present. Properties of a semitransparent object and background in the given two dimensional image are processed to determine the contribution of the background color of the image, the foreground color of the object, and the alpha channel of the object. Once these properties are determined, the accurate stereoscopic rendering of the semitransparent object in front of the background allows the two dimensional image to be converted to three dimensions.

System and method for scaling overlay images

Abstract: A system and method for scaling a composite overlay image, wherein the composite overlay image comprises a plurality of pixels and each pixel comprises at least one color channel and at least one alpha channel, and further wherein at least one pixel of the composite overlay image has an alpha value of zero and a colour value that is not well defined. First, a set of pixels of the composite overlay image are identified as pixels to be dilated. The color channels of the identified pixels are then dilated to form dilated composite overlay image. Finally, the dilated composite overlay image is scaled and combined with a scaled background image.

Image compositing device, image compositing method, and image compositing program

Abstract: PROBLEM TO BE SOLVED: To provide an image compositing device and an image compositing method which have high user response, can hold the quality of an image to be recorded finally at high picture quality, and allow memory capacity to be reduced and to provide an image compositing program. SOLUTION: The image compositing device includes: an intermediate data holding part for holding a detection result obtained by detecting the movement of an object on the basis of at least a plurality of images as intermediate data; an image compositing part for generating a viewer image which is a composite image of the plurality of images; an image holding part for holding the viewer image; and a reprocessing part for performing high picture quality processing for generating a high quality image by using the viewer image and the intermediate data, the image compositing method and the image compositing program are also provided. COPYRIGHT: (C)2009,JPO&INPIT

System and method for DMA controlled image processing

Abstract: A system for processing image data from a plurality of images is disclosed. The invention involves alpha blending of two images of different resolution and color space utilizing shared logic for multiple image streams and without display storage frame buffer. The invention utilizes Direct Memory Access (DMA) fetching module for fetching image data from source images or from source image memory areas and transferring the data to another memory area without having to go through a central processing unit or display storage frame buffer. The DMAs are configured with direct registers or memory mapped descriptors as to the location of the source data. The DMA channels of the DMA module will fetch a portion of the source images (tiling) utilizing a link list or series of descriptors in a certain fetching order. The DMA modules can perform the alpha blending on the fetched image data.

Device and method for interpolating frame

Abstract: PROBLEM TO BE SOLVED: To provide a device 10 for interpolating frames for interpolating the frames of a moving image and smoothing an animation. SOLUTION: The device 10 for interpolating the frames is composed of a motion estimating section 12, a distortion-energy computing section 14, a failure preventive image generating section 16, an alpha-map generating section 18, a motion-compensated warping section 20 and an alpha blending section 22. The reliability of a flow is computed partially on the basis of the flow estimated as an input image. The reliability is warped at the time place of the interpolating frame according to the flow, and converted into an alpha value of 0-1 and an alpha map is generated. The device can also cope with a partial image-quality deterioration by alpha-blending a motion-compensating image and a failure preventive image by the alpha value. COPYRIGHT: (C)2009,JPO&INPIT

Generalised compositing

Abstract: We revisit the assumptions behind traditional image compositing techniques. By analysing the process we separate the colour operations from those for coverage and show that this usefully leads to a more general compositing equation than previously used. We then examine the colour operations in more detail and show how new operations can easily be incorporated in a standard compositor. Practical examples show the new approach and reveal some beneficial effects, not previously achievable within a compositor.

Image compositing apparatus, and image compositing method

Abstract: PROBLEM TO BE SOLVED: To provide an image compositing apparatus and image compositing method for obtaining a proper image from a plurality of images obtained by bracketing photography. SOLUTION: The image compositing apparatus includes: an image data acquiring means for acquiring image data indicating an object, obtained by photographing the object on predetermined photography conditions; a composition ratio setting means for setting the composition ratio of each of a plurality of pieces of image data when combining the plurality of pieces of image data acquired by the image data acquiring means; a combining means for combining the plurality of pieces of image data in accordance with the composition ratios set by the composition ratio setting means; and a display means for displaying thereon an image indicated by the image data composited by the composition means. COPYRIGHT: (C)2008,JPO&INPIT

Image processor, method, and program

Abstract: PROBLEM TO BE SOLVED: To perform more simplified and ideal alpha blending. SOLUTION: A CPU 31 sets an initial value on a plane of a memory 34. A graphic drawing part 38 generates a graphic signal satisfying predetermined relation by generating an image component from the graphic signal supplied from a decoder 37 and drawing the generated image component on the plane. A superposition part 39 performs the more simplified and ideal alpha blending by superposing the graphic signal generated by the graphic drawing part 38 on a television video signal supplied from the decoder 37. This invention is applicable to an image processor. COPYRIGHT: (C)2007,JPO&INPIT

Enhanced alpha blending

Abstract: A system including storage comprising a first graphical pixel and a second graphical pixel. Each of the first and second graphical pixels is associated with binary codes having red, green and blue sub-codes. The system also comprises processing logic coupled to the storage and adapted to alpha-blend the first and second graphical pixels to produce a blended pixel. The processing logic performs this alpha-blend using the binary codes having red, green and blue sub-codes in concatenated form and without operating on the sub-codes individually. The processing logic displays the blended pixel.

Real-time multilayer image synthesis recording system and method, and a recording medium using the system and method

Abstract: Real-time multilayer image synthesis recording system and method, and a recording medium using the system and method are disclosed. The system comprises an image synthesizing unit which synthesizes a chromachannel, background separation image, with a motion image, and further synthesizes with a real-time alpha channel which reacts with sound for thereby generating a 3D multilayer motion image and converting into video and audio files, and a recording unit which stores the video and audio files and a control program into a storing medium in real time, with the control program being able to selectively control the video and audio files.

Automatic real-time facial feature exchange

Abstract: A method of modifying an image, comprising: Receiving a source image of a person's face, wherein the source image is a video image of a live video feed; Detecting a plurality of facial features of the source image; Selecting a target image and at least a first of the facial features by a user, wherein the target image is an image from any source; Detecting a target facial feature in the target image corresponding to the first facial feature; Recovering the first facial feature from the source image; Changing the size of the first facial feature to fit it into the target image; Alpha blending of the changed terms of its size first facial feature; Replacing the target facial feature against the alpha blending subjected first facial characteristic to produce a modified target image, wherein less than 20 percent of the target image to be modified; and Provide the modified target image to an application program.