Terarecon, Inc.

Other

Compaq Computer Corporation, Inc.

Mitsubishi Electric Research Laboratories, Inc.

Trrarecon, Inc.

James M Knittel

Hanspeter Pfister

Jan C Hardenbergh

Hugh C Lauer

Drew R Martin

Larry D Seiler

Kenneth W Correll

Urs H Kanus

William R Peet

Vikram Simha

Takahide Ohkami

Christopher J Kappler

Charidimos E Gasparakis

Vishal C Bhatia

Stephen R Burgess

Frederic H Mokren

Norman Paul Jouppi

Randy B Osborne

Joel James McCormack

Tiecheng T Zhao

Robert Stephen McNamara

Ingmar Bitter

James T Claffey

Jay C Wilkinson

Stephen F Mason

Beverly J Schultz

Frank Clare Dachille

A plurality of identical rendering pipelines are connected in parallel to read an array of voxels and to write an array of pixels. Each pipeline processes one voxel in one processing cycle of the pipelines. Each pipeline includes a plurality of serially connected different stages. The stages can include interpolation, classification, gradient estimation, illumination, and compositing stages. Interfaces connect identical stages in adjacent pipelines as one-way rings to communicate information associated with spatially adjacent voxels, and delay buffers connected parallel to particular stages communicate information associated with temporally adjacent voxels.

Volume rendering pipeline

A volume rendering integrated circuit includes a plurality of interconnected pipelines having stages operating in parallel. The stages of the pipelines are interconnected in a ring, with data being passed in only one direction around the ring. The volume integrated circuit also includes a render controller for controlling the flow of volume data to and from the pipelines and for controlling rendering operations of the pipelines. The integrated circuit may further include interfaces for coupling the integrated circuit to various storage devices and to a host computer.

Volume rendering integrated circuit

A volume rendering processor renders a two-dimensional image from a volume data set of voxels constituting a three-dimensional representation of an object. Voxel memory interface logic retrieves the voxels from a voxel memory in a scanned order with respect to X, Y and Z coordinate axes, the Z axis being the axis most nearly parallel to a predefined viewing direction. The set of voxels having equal Z coordinate values are referred to as a &ldquo;slice&rdquo; of voxels. Interpolation logic calculates a sequence of samples from the retrieved voxels such that (i) each sample lies along a corresponding imaginary ray extending through the object parallel to the viewing direction, (ii) each sample results from interpolating the eight voxels surrounding the sample in the XYZ coordinate system. &ldquo;Supersampling&rdquo; in the Z dimension is performed such that the number of samples calculated for each ray is greater than the number of slices of voxels in the volume data set. Gradient calculation logic calculates for each sample respective gradients in the X, Y and Z directions for use by classification and illumination logic. The X and Y gradients are calculated from the samples emitted by the interpolation logic, and Z gradients are calculated by (i) calculating Z gradients at the voxel positions from voxel values retrieved from memory, and (ii) interpolating the voxel Z gradients to arrive at the Z gradients at the sample positions.

Super-sampling and gradient estimation in a ray-casting volume rendering system

Reflection intensities of volume samples of a volume are mapped in a rendering pipeline by determining a reflection vector from a gradient vector associated with a sample and an eye vector associated with the volume. A diffuse reflectance map is indexed by the gradient vector to obtain a diffuse intensity. A specular reflection map is indexed by the gradient vector to obtain a specular intensity in response to a bypass signal being true, and a specular reflection map is indexed by the reflection vector to obtain the specular intensity in response to the bypass signal being false.

Method and apparatus for mapping reflectance while illuminating volume data in a rendering pipeline

A volume rendering pipeline includes a plurality of processing stages such as a gradient estimation stage, an interpolation stage, a classification stage, an illumination stage, and a compositing stage. The stages are connected to each other by multiplexers. A first multiplexer connects an output of a first stage to an input of a second stage. A second multiplexer connects an output of the second stage to an input of the first stage. A third multiplexer has inputs connected to the output of the first stage and the output of the second stage, the first, second, and third multiplexers are responsive to a select signal to configure the stages of the rendering pipeline for processing the volume data set.

Configurable volume rendering pipeline

Samples of a volume are lighted in a rendering pipeline by having a first arithmetic unit combine a modulated emissive coefficient with a modulated diffuse coefficient and a modulated diffuse intensity. A second arithmetic logic unit combines a specular coefficient with a modulated specular intensity and an opacity component of the sample. A third arithmetic unit combines the output of the second arithmetic logic unit and specular colors of the sample. A fourth arithmetic logic unit combines the output of the first arithmetic unit with colors of the sample, and a fifth arithmetic logic unit combines the output of the third and fourth arithmetic units to illuminate the sample.

Method and apparatus for applying modulated lighting to volume data in a rendering pipeline

A volume data set having voxels arranged according to an object coordinate system is shear-warp rendered by partitioning, relative to the object coordinate system, the volume data set into a plurality of axis aligned sets of voxels. The selected axis aligned sets of voxels are rendered as pixels in intermediate baseplanes. There is one intermediate baseplane for each selected set of axis aligned voxels. The intermediate baseplanes are combined and warped to an image.

Rendering a shear-warped partitioned volume data set

A method modulates volume samples in an illumination stage of a volumetric rendering pipeline. The method determines a magnitude of a gradient vector of a volume sample. The gradient vector has components G G and G . The squares of the components are summed to determine a squared gradient magnitude &verbar;G &verbar;. The square root of the squared magnitude &verbar;G &verbar; is taken to determine the magnitude &verbar;G&verbar; of the gradient vector. A step value in a gradient magnitude range is then specified. A high pass modulation factor is set to zero if the magnitude is less than the step value, and to one otherwise to modulate the volume sample with a step function.

Method for modulating volume samples with gradient magnitude vectors and step functions

A method modulates samples in a volume rendering pipeline by storing modulation values as entries in a table. Also stored are a grain and a base for the entries of the table to specify an index range. A magnitude of a gradient vector of a sample is determined. The table is indexed using the magnitude to determine two modulation values corresponding to the magnitude. The two modulation values are interpolated using the grain and the base to determine a modulation factor to modulate the sample with a linear function.

Method for modulating volume samples using gradient magnitudes and complex functions over a range of values

An apparatus generates lighting modulation factors for samples in a volume rendering pipeline. The apparatus includes a first arithmetic logic unit squaring a gradient magnitude vector of a sample to produce a squared gradient magnitude. A second arithmetic logic unit produces a gradient magnitude from the squared gradient magnitude. A shift register, connected to the first arithmetic logic unit, truncates a predetermined number of high bits of the squared gradient magnitude. A gradient magnitude modulation register stores modulation parameters. A first multiplexer, connected to the second arithmetic logic unit and the shift register, selects the truncated squared gradient magnitude as an index if an index source signal is true, and the gradient magnitude if the index source signal is false, and a memory table is indexes by the index to produce modulated opacity, emissive, diffuse and specular modulation factors.

Method and apparatus for modulating lighting with gradient magnitudes of volume data in a rendering pipeline

An apparatus illuminates samples in a volume rendering pipeline. The apparatus includes the following units. A gradient magnitude modulation unit produces an opacity, emissive, diffuse and specular modulation factor from a gradient magnitude vector of each sample. A reflectance mapping unit produces a diffuse intensity and a specular intensity from the gradient magnitude vector of each sample and an eye vector of the volume. A first arithmetic logic unit combines an opacity of each sample with the corresponding opacity modulation factor to generate modulated opacities. A second arithmetic logic unit combines an emissive coefficient with the emissive modulation factor of each sample to generate modulated emissive coefficients. A third arithmetic logic unit combines the diffuse intensity with the diffuse modulation factor of each sample to generate modulated diffuse intensities. A fourth arithmetic logic unit combines the specular intensity with the specular modulation factor of each sample to generate modulated specular intensities, and a lighting unit applies the modulated emissive coefficient, modulated diffuse and specular intensities to color components of the samples to illuminate the volume sample.

Method and apparatus for illuminating volume data in a rendering pipeline

A computer graphics system renders an image on a display device using improved pre-filtering techniques that minimize aliasing artifacts in the image, particularly at the endpoints of lines. To anti-alias the image, a plurality of edges are placed near a line in the image. An edge function represents the edge. This edge function is multiplied by a scale factor to produce a distance function. This scale factor is the reciprocal of the Euclidean length of the line. The distance function is evaluated to determine the distance of selected pixels from each edge in units of pixels. These distances determine the intensity value for each selected pixel. Pixels on or beyond an edge, with respect to the line, are given a minimum intensity value; pixels inside all edges are given intensity values corresponding to their distances from the edge. An intensity function describing a relationship between pixel distances from the edges and their corresponding intensity values is developed. The intensity function can be implemented in a look-up table or approximated with hardware.

Pre-filtered antialiased lines using distance functions

A low-cost, real-time volume rendering system including a three-dimensional cursor for interactively identifying and marking positions within a three-dimensional volume data set during display is disclosed. The cursor appearance is configurable such that it may appear as cross hairs, cross planes, or some combination thereof, with each cursor dimension being selectively enabled. Each cursor dimension is configurable in terms of color and level of opacity. The shape of the edges and the appearance of the intersection of the dimensions is configurable, and the colors of the individual cursor components may alternately blend or obscure the colors of the objects behind them. The cursor is realized through use of a comparison circuit operating in conjunction with a parallel pipeline processor optimized for volume rendering using a ray-casting technique. The comparison circuit checks whether the data sample is taken from a region of the three-dimensional object which may be affected by the presence of a three-dimensional cursor. Voxels which collectively define the object are ordered according to a given three-dimensional coordinate system; the desired cursor is also defined with respect to this coordinate system.

Three-dimensional cursor for a real-time volume rendering system

A two-level skewing architecture is imposed on the memory subsystem of a volume rendering system in which voxel data is stored in mini-blocks assigned to a set of DRAM memory modules, thereby permitting data transfer at the maximum burst rate of the DRAM memory and enabling real-time volume rendering. Within each DRAM module, mini-blocks are assigned to the memory banks so that consecutively accessed mini-blocks are assigned to different banks, thereby avoiding idle cycles during data transfer and increasing DRAM transfer efficiency to nearly 100%. In one embodiment, read-out of voxel data from banks of the DRAM memory proceeds from left to right unless there is a conflict of banks, in which case the read-out order is reversed. A specialized de-skewing network is provided to re-order the voxel data read out from DRAM memory so that the voxels can be processed in the order which they are arranged in the volume data set rather than the order in which they are stored in memory.

Two-level mini-block storage system for volume data sets

A volume rendering processor establishes a cut-plane region of a volume data set, the cut-plane region being defined by a plane equation and minimum and maximum distance values representing the values of the plane equation at outer faces of the cut-plane region. The plane equation is evaluated for each sample of the volume data, the result is compared with the minimum and maximum distance values to determine whether the sample is in the cut-plane region, and the visibility of the sample is adjusted depending on the comparison result. The plane equation is evaluated by continually accumulating the coefficient values in an order indicated by the ordering of the sequence of samples. Evaluation logic includes an accumulator, a 2-input adder, registers for saving intermediate accumulated values in corresponding dimensions of the volume data, multiplexers for selecting the adder inputs from among the coefficient values, the output of the accumulator and the values in the registers, and visibility calculation logic that adjusts the samples' visibility depending on the relationship between the output of the accumulator and the minimum and maximum distance values. In an inclusive operating mode, the visibility of the sample is set to zero if it is outside the cut-plane region, and in an exclusive mode the sample's visibility is set to zero if it lies in the cut-plane region. Falloff regions at each face of the cut-plane region are used to gradually adjust sample visibility to provide a smooth appearance.

Growing community of inventors

Groton, MA, United States of America

James M Knittel