Alpha compositing

About: Alpha compositing is a research topic. Over the lifetime, 482 publications have been published within this topic receiving 11035 citations. The topic is also known as: alpha blend & alpha channel.

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.

A Vector-based Representation for Image Warping

Abstract: A method for image analysis, representation and re-synthesis is introduced. Unlike other schemes it is not pixel based but rather represents a picture as vector data, from which an altered version of the original image can be rendered. Representing an image as vector data allows performing operations such as zooming, retouching or colourising, avoiding common problems associated with pixel image manipulation. This paper brings together methods from the areas of computer vision, image compositing and image based rendering to prove that this type of image representation is a step towards accurate and efficient image manipulation.

Method and device for volume rendering image processing and program therefor

Abstract: PROBLEM TO BE SOLVED: To provide a method and a device for volume rendering image processing and a program therefor which can provide images on which a plurality of objects(tissues or the like) overlapped along the line of sight are well observed. SOLUTION: A first image 31 is acquired by performing volume rendering under an opacity value set to draw only first tissues (bones) 50 clearly by using CT image data. A second image 32 is acquired by performing volume rendering under an opacity value set to draw only second tissues (blood vessels) 51 clearly by using the CT image data. The first and second images are treated by alpha blending. For example, if the alpha blending is performed on the images with a blending ratio of 0.5:0.5, an image clearly showing both of the first tissues (bones) 50 and the second tissues (blood vessels) 51 is acquired (Figure (b)). COPYRIGHT: (C)2004,JPO&NCIPI

Mixed-order compositing for images having three-dimensional painting effects

Abstract: Rendering 3D paintings can be done by compositing brush strokes embedded in space. Image elements are rendered into an image representable by a pixel array wherein at least some of the image elements correspond to simulated painting strokes. A method may include determining stroke positions in a 3D space, determining stroke orders, and for each pixel to be addressed, determining a pixel color value by determining strokes intersections with a view ray for that pixel, determining a depth order and a stroke order for intersecting fragments, each fragment having a color, alpha value, depth, and stroke order, assigning an intermediate color to each of the fragments, corresponding to a compositing of nearby fragments in stroke order, and assigning a color to the pixel that corresponds to a compositing of the fragments using the intermediate colors assigned to the fragments. The compositing may be done in depth order.

Fast Soft Color Segmentation

Abstract: We address the problem of soft color segmentation, defined as decomposing a given image into several RGBA layers, each containing only homogeneous color regions. The resulting layers from decomposition pave the way for applications that benefit from layer-based editing, such as recoloring and compositing of images and videos. The current state-of-the-art approach for this problem is hindered by slow processing time due to its iterative nature, and consequently does not scale to certain real-world scenarios. To address this issue, we propose a neural network based method for this task that decomposes a given image into multiple layers in a single forward pass. Furthermore, our method separately decomposes the color layers and the alpha channel layers. By leveraging a novel training objective, our method achieves proper assignment of colors amongst layers. As a consequence, our method achieve promising quality without existing issue of inference speed for iterative approaches. Our thorough experimental analysis shows that our method produces qualitative and quantitative results comparable to previous methods while achieving a 300,000x speed improvement. Finally, we utilize our proposed method on several applications, and demonstrate its speed advantage, especially in video editing.