Graphics

CPU Ray tracing in scientific visualization has been shown to be an efficient rendering algorithm for large-scale polygonal data on distributed-memory systems by using custom integrations which modify the source code of existing visualization tools or by using OpenGL interception to run without source code modification to existing tools. Previous implementations in common visualization tools use existing data-parallel work distribution with sort-last compositing algorithms and exhibited sub-optimal performance scaling across multiple nodes due to the inefficiencies of data-parallel distributions of the scene geometry. This paper presents a solution which uses efficient ray tracing through OpenGL interception using an image-parallel work distribution implemented on top of the data-parallel distribution of the host program while supporting a paging system for access to non-resident data. Through a series of scaling studies, we show that using an image-parallel distribution often provides superior scaling performance which is more independent of the data distribution and view, while also supporting secondary rays for advanced rendering effects.

This paper details a method for interactive direct volume rendering that computes ambient occlusion effects for visualizations that combine both volumetric and geometric primitives, specifically tube shaped geometric objects representing streamlines, magnetic field lines or DTI fiber tracts. The algorithm extends the recently presented Directional Occlusion Shading model to allow the rendering of those geometric shapes in combination with a context providing 3D volume, considering mutual occlusion between structures represented by a volume or geometry. Stream tube geometries are computed using an effective spline based interpolation and approximation scheme that avoids self intersection and maintains coherent orientation of the stream tube segments to avoid surface deforming twists. Furthermore, strategies to reduce the geometric and specular aliasing of the stream tubes are discussed.

Multivariate volumetric datasets are important to both science and medicine. We propose a transfer function (TF) design approach based on user selected samples in the spatial domain to make multivariate volumetric data visualization more accessible for domain users. Specifically, the user starts the visualization by probing features of interest on slices and the data values are instantly queried by user selection. The queried sample values are then used to automatically and robustly generate high dimensional transfer functions (HDTFs) via kernel density estimation (KDE). Alternatively, 2D Gaussian TFs can be automatically generated in the dimensionality reduced space using these samples. With the extracted features rendered in the volume rendering view, the user can further refine these features using segmentation brushes. Interactivity is achieved in our system and different views are tightly linked. Use cases show that our system has been successfully applied for simulation and complicated seismic data sets.

Conventional shadow mapping relies on uniform sampling for producing hard shadow in an efficient manner. This approach trades image quality in favor of efficiency. A number of approaches improve upon shadow mapping by combining multiple shadow maps or using complex data structures to produce shadow maps with multiple resolutions. By sacrificing some performance, these adaptive methods produce shadows that closely match ground truth.

This paper introduces Rectilinear Texture Warping (RTW) for efficiently generating adaptive shadow maps. RTW images combine the advantages of conventional shadow mapping - a single shadow map, quick construction, and constant time pixel shadow tests, with the primary advantage of adaptive techniques - shadow map resolutions which more closely match those requested by output images. RTW images consist of a conventional texture paired with two 1-D warping maps that form a rectilinear grid defining the variation in sampling rate. The quality of shadows produced with RTW shadow maps of standard resolutions, i.e. 2,048×2,048 texture for 1080p output images, approaches that of raytraced results while low overhead permits rendering at hundreds of frames per second.

A fundamental step in stitching several pictures to form a larger mosaic is the computation of boundary seams that minimize the visual artifacts in the transition between images. Current seam computation algorithms use optimization methods that may be slow, sequential, memory intensive, and prone to finding suboptimal solutions related to local minima of the chosen energy function. Moreover, even when these techniques perform well, their solution may not be perceptually ideal (or even good). Such an inflexible approach does not allow the possibility of user-based improvement. This paper introduces the Panorama Weaving technique for seam creation and editing in an image mosaic. First, Panorama Weaving provides a procedure to create boundaries for panoramas that is fast, has low memory requirements and is easy to parallelize. This technique often produces seams with lower energy than the competing global technique. Second, it provides the first interactive technique for the exploration of the seam solution space. This powerful editing capability allows the user to automatically extract energy minimizing seams given a sparse set of constraints. With a variety of empirical results, we show how Panorama Weaving allows the computation and editing of a wide range of digital panoramas including unstructured configurations.

Ray tracing in scientific visualization allows for substantial gains in performance and rendering quality with large scale polygonal datasets compared to brute-force rasterization, however implementing new rendering architectures into existing tools is often costly and time consuming. This paper presents a library, GLuRay, which intercepts OpenGL calls from many common visualization applications and renders them with the CPU ray tracer Manta without modification to the underlying visualization tool. Rendering polygonal models such as isosurfaces can be done identically to an OpenGL implementation using provided material and camera properties or superior rendering can be achieved using enhanced settings such as dielectric materials or pinhole cameras with depth of field effects. Comparative benchmarks were conducted on the Texas Advanced Computing Center’s Longhorn cluster using the popular visualization packages ParaView, VisIt, Ensight, and VAPOR. Through the parallel ren- dering package ParaView, scaling up to 64 nodes is demonstrated. With our tests we show that using OpenGL interception to accelerate and enhance visualization programs provides a viable enhancement to existing tools with little overhead and no code modification while allowing for the creation of publication quality renderings using advanced effects and greatly improved large-scale software rendering performance within tools that scientists are currently using.

Large-scale analysis and visualization is becoming increasingly important as supercomputers and their simulations produce larger and larger data. These large data sizes are pushing the limits of traditional rendering algorithms and tools thus motivating a study exploring these limits and their possible resolutions through alternative rendering algorithms . In order to better understand real-world performance with large data, this paper presents a detailed timing study on a large cluster with the widely used visualization tools ParaView and VisIt. The software ray tracer Manta was integrated into these programs in order to show that improved performance could be attained with software ray tracing on a distributed memory, GPU enabled, parallel visualization resource. Using the Texas Advanced Computing Center’s Longhorn cluster which has multi-core CPUs and GPUs with large-scale polygonal data, we find multi-core CPU ray tracing to be significantly faster than both software rasterization and hardware-accelerated rasterization in existing scientific visualization tools with large data.

We introduce a novel mid-structure called the generalized swept mid-structure (GSM) of a closed polygonal shape, and a framework to compute it. The GSM contains both curve and surface elements and has consistent sheet-by-sheet topology, versus triangle-by-triangle topology produced by other mid-structure methods. To obtain this structure, a harmonic function, defined on the volume that is enclosed by the surface, is used to decompose the volume into a set of slices. A technique for computing the 1D mid-structures of these slices is introduced. The mid-structures of adjacent slices are then iteratively matched through a boundary similarity computation and triangulated to form the GSM. This structure respects the topology of the input surface model is a hybrid mid-structure representation. The construction and topology of the GSM allows for local and global simplification, used in further applications such as parameterization, volumetric mesh generation and medical applications.

Direct volume rendering has been an active area of research for over two decades. Transfer function design remains a difficult task since current methods, such as traditional 1D and 2D transfer functions are not always effective for all datasets. Various 1D or 2D transfer function spaces have been proposed to improve classification exploiting different aspects, such as using the gradient magnitude for boundary location and statistical, occlusion, or size metrics. In this paper, we present a novel transfer function method which can provide more specificity for data classification by combining different transfer function spaces. In this work, a 2D transfer function can be combined with 1D transfer functions which improve the classification. Specifically, we use the traditional 2D scalar/gradient magnitude, 2D statistical, and 2D occlusion spectrum transfer functions and combine these with occlusion and/or size-based transfer functions to provide better specificity. We demonstrate the usefulness of the new method by comparing to the following previous techniques: 2D gradient magnitude, 2D occlusion spectrum, 2D statistical transfer functions and 2D size based transfer functions.

In this paper, a method for interactive direct volume rendering is proposed that computes ambient occlusion effects for visualizations that combine both volumetric and geometric primitives, specifically tube shaped geometric objects representing streamlines, magnetic field lines or DTI fiber tracts. The proposed algorithm extends the recently proposed Directional Occlusion Shading model to allow the rendering of those geometric shapes in combination with a context providing 3D volume, considering mutual occlusion between structures represented by a volume or geometry.

Bounding volume hierarchies (BVHs) are a popular acceleration structure choice for animated scenes rendered with ray tracing. This is due to the relative simplicity of refitting bounding volumes around moving geometry. However, the quality of such a refitted tree can degrade rapidly if objects in the scene deform or rearrange significantly as the animation progresses, resulting in dramatic increases in rendering times and a commensurate reduction in the frame rate. The BVH could be rebuilt on every frame, but this could take significant time. We present a method to efficiently extend refitting for animated scenes with tree rotations, a technique previously proposed for off-line improvement of BVH quality for static scenes. Tree rotations are local restructuring operations which can mitigate the effects that moving primitives have on BVH quality by rearranging nodes in the tree during each refit rather than triggering a full rebuild. The result is a fast, lightweight, incremental update algorithm that requires negligible memory, has minor update times, parallelizes easily, avoids significant degradation in tree quality or the need for rebuilding, and maintains fast rendering times. We show that our method approaches or exceeds the frame rates of other techniques and is consistently among the best options regardless of the animated scene.

Gradient domain processing remains a particularly computationally expensive technique even for relatively small images. When images become massive in size, giga or terapixel, these problems become particularly troublesome and the best serial techniques take on the order of hours or days to compute a solution. In this paper, we provide a simple framework for the parallel gradient domain processing. Specifically, we provide a parallel out-of-core method for the seamless stitching of gigapixel panoramas in a parallel MPI environment. Unlike existing techniques, the framework provides both a straightforward implementation, maintains strict control over the required/allocated resources, and makes no assumptions on the speed of convergence to an acceptable image. Furthermore, the approach shows good weak/strong scaling from several to hundreds of cores and runs on a variety of hardware.

We present a state of the art read-only distributed shared memory (DSM) ray tracer capable of fully utilizing modern cluster hardware to render massive out-of-core polygonal models at real-time frame rates. Achieving this required adapting a state of the art packetized BVH acceleration structure for use with DSM and modifying the mesh and BVH data layouts to minimize communication costs. Furthermore, several design decisions and optimizations were made to take advantage of InfiniBand interconnects and multi-core machines.

In this paper, a method for interactive direct volume rendering is proposed for computing depth of field effects, which previously were shown to aid observers in depth and size perception of synthetically generated images. The presented technique extends those benefits to volume rendering visualizations of 3D scalar fields from CT/MRI scanners or numerical simulations. It is based on incremental filtering and as such does not depend on any precomputation, thus allowing interactive explorations of volumetric data sets via on-the-fly editing of the shading model parameters or (multi-dimensional) transfer functions.

We accelerate the finding of occluders in tree based acceleration structures, such as a packetized BVH and a single ray kd-tree, by deriving the ray termination surface area heuristic (RTSAH) cost model for traversing an occlusion ray through a tree and then using the RTSAH to determine which child node a ray should traverse first instead of the traditional choice of traversing the near node before the far node. We further extend RTSAH to handle materials that attenuate light instead of fully occluding it, so that we can avoid superfluous intersections with partially transparent objects. For scenes with high occlusion, we substantially lower the number of traversal steps and intersection tests and achieve up to 2x speedups.

This article presents a simple framework for progressive processing of high-resolution images with minimal resources. We demonstrate this framework's effectiveness by implementing an adaptive, multi-resolution solver for gradient-based image processing that, for the first time, is capable of handling gigapixel imagery in real time. With our system, artists can use commodity hardware to interactively edit massive imagery and apply complex operators, such as seamless cloning, panorama stitching, and tone mapping.

We introduce a progressive Poisson solver that processes images in a purely coarse-to-fine manner, providing near instantaneous global approximations for interactive display (see Figure 1). We also allow for data-driven adaptive refinements to locally emulate the effects of a global solution. These techniques, combined with a fast, cache-friendly data access mechanism, allow the user to interactively explore and edit massive imagery, with the illusion of having a full solution at hand. In particular, we demonstrate the interactive modification of gigapixel panoramas that previously required extensive offline processing. Even with massive satellite images surpassing a hundred gigapixels in size, we enable repeated interactive editing in a dynamically changing environment. Images at these scales are significantly beyond the purview of previous methods yet are processed interactively using our techniques. Finally our system provides a robust and scalable out-of-core solver that consistently offers high-quality solutions while maintaining strict control over system resources.

The method of Moving Least Squares (MLS) is a popular framework for reconstructing continuous functions from scattered data due to its rich mathematical properties and well-understood theoretical foundations. This paper applies MLS to volume rendering, providing a unified mathematical framework for ray casting of scalar data stored over regular as well as irregular grids. We use the MLS reconstruction to render smooth isosurfaces and to compute accurate derivatives for high-quality shading effects. We also present a novel, adaptive preintegration scheme to improve the efficiency of the ray casting algorithm by reducing the overall number of function evaluations, and an efficient implementation of our framework exploiting modern graphics hardware. The resulting system enables high-quality volume integration and shaded isosurface rendering for regular and irregular volume data.