Showing papers on "Alpha compositing published in 2010"

Multi-scale image harmonization

Abstract: Traditional image compositing techniques, such as alpha matting and gradient domain compositing, are used to create composites that have plausible boundaries. But when applied to images taken from different sources or shot under different conditions, these techniques can produce unrealistic results. In this work, we present a framework that explicitly matches the visual appearance of images through a process we call image harmonization, before blending them. At the heart of this framework is a multi-scale technique that allows us to transfer the appearance of one image to another. We show that by carefully manipulating the scales of a pyramid decomposition of an image, we can match contrast, texture, noise, and blur, while avoiding image artifacts. The output composite can then be reconstructed from the modified pyramid coefficients while enforcing both alpha-based and seamless boundary constraints. We show how the proposed framework can be used to produce realistic composites with minimal user interaction in a number of different scenarios.

Error-tolerant image compositing

Abstract: Gradient-domain compositing is an essential tool in computer vision and its applications, e.g., seamless cloning, panorama stitching, shadow removal, scene completion and reshuffling. While easy to implement, these gradient-domain techniques often generate bleeding artifacts where the composited image regions do not match. One option is to modify the region boundary to minimize such mismatches. However, this option may not always be sufficient or applicable, e.g., the user or algorithm may not allow the selection to be altered. We propose a new approach to gradient-domain compositing that is robust to inaccuracies and prevents color bleeding without changing the boundary location. Our approach improves standard gradient-domain compositing in two ways. First, we define the boundary gradients such that the produced gradient field is nearly integrable. Second, we control the integration process to concentrate residuals where they are less conspicuous. We show that our approach can be formulated as a standard least-squares problem that can be solved with a sparse linear system akin to the classical Poisson equation. We demonstrate results on a variety of scenes. The visual quality and run-time complexity compares favorably to other approaches.

Simulating Low-Cost Cameras for Augmented Reality Compositing

Abstract: Video see-through Augmented Reality adds computer graphics to the real world in real time by overlaying graphics onto a live video feed. To achieve a realistic integration of the virtual and real imagery, the rendered images should have a similar appearance and quality to those produced by the video camera. This paper describes a compositing method which models the artifacts produced by a small low-cost camera, and adds these effects to an ideal pinhole image produced by conventional rendering methods. We attempt to model and simulate each step of the imaging process, including distortions, chromatic aberrations, blur, Bayer masking, noise, sharpening, and color-space compression, all while requiring only an RGBA image and an estimate of camera velocity as inputs.

Accelerating and benchmarking radix-k image compositing at large scale

Abstract: Radix-k was introduced in 2009 as a configurable image compositing algorithm. The ability to tune it by selecting k-values allows it to benefit more from pixel reduction and compression optimizations than its predecessors. This paper describes such optimizations in Radix-k, analyzes their effects, and demonstrates improved performance and scalability. In addition to bounding and run-length encoding pixels, k-value selection and load balance are regulated at run-time. Performance is systematically analyzed for an array of process counts, image sizes, and HPC and graphics clusters. Analyses are performed using compositing of synthetic images and also in the context of a complete volume renderer and scientific data. We demonstrate increased performance over binary swap and show that 64 megapixels can be composited at rates of 0.08 seconds, or 12.5 frames per second, at 32 K processes.

Real-Time Chromakey Matting Using Image Statistics

Abstract: A method, system and computer readable media for real-time chromakey matting using image statistics. To identify the chroma key spectrum, the system/method executes in three stages. In an off-line training stage, the system performs semi-automatic calibration of the chroma key parameterization. In the real-time classification stage, the system estimates the alpha matte on a GPU. Finally, an optional error minimization stage improves the estimated matte, accounting for misclassifications and signal noise. Given the resulting matte, standard alpha blending composites the virtual scene with the video feed to create the illusion that both worlds coexist.

Fast compositing for cluster-parallel rendering

Abstract: The image compositing stages in cluster-parallel rendering for gathering and combining partial rendering results into a final display frame are fundamentally limited by node-to-node image throughput. Therefore, efficient image coding, compression and transmission must be considered to minimize that bottleneck. This paper studies the different performance limiting factors such as image representation, region-of-interest detection and fast image compression. Additionally, we show improved compositing performance using lossy YUV subsampling and we propose a novel fast region-of-interest detection algorithm that can improve in particular sort-last parallel rendering.

Method and apparatus for reconstructing a high-resolution image by using multi-layer low-resolution images

Abstract: A method of reconstructing a high-resolution image by using multi-layer low-resolution images includes dividing a low-resolution image into a plurality of texture layer low-resolution images and a plurality of base layer low-resolution images; generating a texture layer high-resolution image by compositing the plurality of the texture layer low-resolution images and generating a base layer high-resolution image by compositing the plurality of the base layer low-resolution images; and outputting a high-resolution image by compositing the texture layer high-resolution image and the base layer high-resolution image.

Converting continuous tone images

Abstract: One or more techniques and/or systems are disclosed for converting an unsupported continuous tone image file with an opacity layer to an application supported image. An opacity mask is created from an extracted alpha channel portion of the unsupported image file, where the alpha channel comprises transparency (opacity) information for the image. The unsupported image file can comprise an eight-bit alpha channel that indicates transparency for one or more portions of the image. The remaining channels of the unsupported image, after the alpha channel is extracted, can be used to create an image, which is combined with the opacity mask, to generate a supported image with a transparency layer.

Method of creating a printable raster image file

Abstract: A method of creating a printable raster image file from a PDL file, including interpreting the PDL file, thereby to create a display list; and applying raster image processing to the display list, thereby to create the printable raster image file in four separation colours (C, M, Y, K), wherein the raster image processing is performed in a Graphics Processing Unit (GPU) having three colour channels (R, G, B) and an alpha channel (A) for transparency, and the three colour channels and the alpha channel are mapped onto the four separation colours (C, M, Y, K).

Image processing using linear parametres of lighting apparatus and other image processng enhancements

Abstract: FIELD: information technology. ^ SUBSTANCE: processing involves scaling, creation of composite images, alpha blending, edge detection etc. A more specific realisation describes strategies for processing image information which: a) is linear; b) lies in the colour space RGB; c) has high accuracy (e.g. provided through floating-point representation); d) is row-wise; and e) is full-channel. Other enhancements provide strategies for: a) processing image information in pseudolinear space in order to increase rate of processing; b) realising an improved error variance technique; c) dynamic calculation and use of filtration nuclei; d) optimising pipelined code generation; and e) realising different processing tasks using novel pixel shader techniques. ^ EFFECT: reduced image distortion. ^ 20 cl, 21 dwg

Avionics device display dimming system and method

Abstract: The present general inventive concept provides a system and method to use alpha blending properties of a graphics processor to dim the display, effectively darkening it with neutral color overlays, beyond the last hardware dimming step.

Authentication of binary document images in PNG format based on a secret sharing technique

Abstract: A new authentication method utilizing the secret sharing technique to resist attacks with a data recovery capability for binary document images in PNG format is proposed. An authentication signal is generated for each block of a cover image, which together with the block content is transformed into several shares using the Shamir secret sharing scheme. The shares then are embedded into the alpha channel plane of the input PNG image in a carefully designed manner. In the process of image authentication, an image block is marked as tampered if the authentication signal computed from the current block content does not match that extracted from the shares embedded in the alpha channel plane. Data recovery is conducted for each tampered block by a reverse Shamir scheme after collecting enough shares from unmarked blocks. Experimental results prove the effectiveness of the proposed method for real applications.

Efficient pipelining parallel methods for image compositing in sort-last rendering

Abstract: It is well known that image compositing is the bottleneck in Sort-Last rendering. Many methods have been developed to reduce the compositing time. In this paper, we present a series of pipeline methods for image compositing. Our new pipeline methods based on Direct Send and Binary Swap. However, unlike these methods, our methods overlap the rendering time of different frames to achieve high fps(frames per second) in final display. We analyze the theoretical performance of our methods and take intensive experiments using real data. The results show that our new methods are able to achieve interactive frame rates and scale well with both the size of nodes and screen resolution.

Improved Algorithm on Digital Image Matting

Abstract: Digital image matting is to extract the foreground objects with arbitrary shapes from an image. This paper proposes optimal and developed algorithms for image matting in the efficiency and user interaction, without solving an optimization problem, but transforms the optimization problem into the minimum weighted distance issues based on dynamic programming. This method begins from segmenting regions by a user with two different colors to identify the foreground and background, and then the algorithm will be automatically propagated according to sampling points. Thus we can calculate the alpha channel of the overall image. This method is much faster than the existing approaches of comparable quality.

Difpainter: Take image difference as paint in digital painting

Abstract: To introduce real materials into digital painting, the interactive digital painting system “Difpainter” is proposed. The rudiment of this system is the calculation of difference between images captured from video camera. The system first captures two images from video camera, and then calculates the difference of the two and yields foreground image, finally paint target image with the foreground image by alpha blending technology. This process is executed iteratively; the parameters are configured through graphic user interface. The system enables using webcam to practice “Light Painting” and some other novel painting skills. This research enriches the skills of digital painting, improves the user experience, and presents novel visual effects.

A new compression-based image composition strategy on sort-last parallel rendering system

Abstract: The cluster computer based parallel rendering is an effective method to build applications with better performance and higher resolution. Compression-based image composition is the key component of sort-last parallel rendering system. In this paper, we propose a set of strategies for compression-based image composition on sort-last parallel rendering system. Our strategy consists of three algorithms: A template-based LZW lossless compression method and a depth-buffer interpolation method to deal with the depth information of the images; A JPEG-based chromatic information compression method; and a composition method based on alpha blending. The experimental results show that our strategy is more effective than traditional compression based image composition strategies when used on sort-last parallel rendering system.

Design of Multi-channel Image Superimposition System Based on FPGA

Abstract: A multi-channel image superimposition system is designed in this paper. It can superimpose white-light image on infrared thermal image to generate mixture image. The system is realized on a FPGA chip and is mainly composed of multi-channle DMA controller and image superimposition module. Multi-channel DMA controller can realize data exchange between image superimpositon module and memory independent of vehicle-loaded CPU. Image superimposition module adopts Alpha channel mixture algrithm to mix two-channel images. Equations of algrithm are modified to forms that can be easily designed on a FPGA chip. Due to using programmable chips and parallel processing technology, the system has high integration, good maintenance, quick image processing speed and strong real-time capability.

Video processing device

Abstract: A video processing device includes a sprite rendering processor in connection with a display buffer (e.g. line buffers) and an alpha table. The sprite rendering processor alternately performs first rendering based on sprite attribute data and second rendering based on alpha attribute data. The first rendering is performed via alpha blending on video data of sprites, rendering-destination video data of the display buffer, and rendering-destination alpha data of the alpha buffer which are produced via the second rendering with the alpha buffer, thus producing resultant video data, which is written over rendering-destination video data in the display buffer. One type of sprite is connected with at least one alpha table which describes alpha data ranging from perfect transparency and perfect non-transparency and which is optimized to demonstrate an anti-aliasing effect on the boundary of a colored region of each sprite on the screen of a visual display.