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.

Interpolation of pixel values and alpha values in a computer graphics display device

Abstract: Interpolating a low or medium resolution image to a higher resolution image using a pixel replication and averaging technique. An overlay image having pixels of a first display resolution and a plurality of alpha blending values each indicating the degree of blending with a background image is interpolated to the resolution of the background image. In addition to interpolating pixel values, alpha blending values are themselves interpolated and multiplied by corresponding overlay pixel values prior to being blended with the background image.

Compositing. 1. Theory

Abstract: Associating a pixel's color with its opacity is the basis for a compositing function that is simple, elegant, and general. However, there are more reasons than mere prettiness to store pixels this way. One of the most important anti-aliening tools in computer graphics comes from a generalization of the simple act of storing a pixel into a frame buffer. Several people simultaneously discovered the usefulness of this operation, so it goes by several names: matting, image compositing, alpha blending, overlaying, or lerping. It was most completely codified in a previous paper by Porter and Duff (1984), where they call it the over operator. The author shows a new way to derive the over operator and describes some implementation details that he has found useful. >

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.

Method and apparatus for high performance antialiasing which minimizes per pixel storage and object data bandwidth

Abstract: The present invention is an improved system and method of antialiasing which generates a coverage mask which is retained long enough to achieve geometric precision. The coverage mask information is retained throughout the compositing stage of the image generation. A system for antialiasing an image according to the present invention is comprised of a means for compositing an image, wherein the image is composited using coverage mask data of a pixel, and means for storage of data during image compositing, the storage means coupled to the compositing means.

Visibility sorting and compositing without splitting for image layer decompositions

Abstract: We present an efficient algorithm for visibility sorting a set of moving geometric objects into a sequence of image layers which are composited to produce the final image. Instead of splitting the geometry as in previous visibility approaches, we detect mutual occluders and resolve them using an appropriate image compositing expression or merge them into a single layer. Such an algorithm has many applications in computer graphics; we demonstrate two: rendering acceleration using image interpolation and visibility-correct depth of field using image blurring. We propose a new, incremental method for identifying mutually occluding sets of objects and computing a visibility sort among these sets. Occlusion queries are accelerated by testing on convex bounding hulls; less conservative tests are also discussed. Kd-trees formed by combinations of directions in object or image space provide an initial cull on potential occluders, and incremental collision detection algorithms are adapted to resolve pairwise occlusions, when necessary. Mutual occluders are further analyzed to generate an image compositing expression; in the case of nonbinary occlusion cycles, an expression can always be generated without merging the objects into a single layer. Results demonstrate that the algorithm is practical for real-time animation of scenes involving hundreds of objects each comprising hundreds or thousands of polygons. CR Categories: I.3.3 [Computer Graphics]: Picture/Image Generation Display algorithms. Additional