Abstract

Graphics models are getting increasingly bulkier with de-tailed geometry, textures, normal maps, etc. There is a lotof interest to model and navigate through detailed models oflarge monuments. Many monuments of interest have bothrich detail and large spatial extent. Rendering them for navi-gation on a single workstation is practically impossible, evengiven the power of today’s CPUs and GPUs. Many modelsmay not fit the GPU memory, the CPU memory, or eventhe secondary storage of the CPU. Distributed renderingusing a cluster of workstations is the only way to navigatethrough such models. In this paper, we present a design ofa distributed rendering system intended for massive mod-els. Our design has a server that holds the skeleton of thewhole model, namely, its scenegraph with actual geometryreplaced by bounding boxes at all levels. The server dividesthe screen space among a number of clients and sends thema list of objects they need to render using a frustum cullingstep. The clients use 2 GPUs with one devoted to visibilityculling and the other to rendering. Frustum culling at theserver, visibility culling on one GPU, and rendering on thesecond GPU form the stages of our distributed renderingpipeline. We describe the design and implementation of oursystem and demonstrate the results of rendering relativelylarge models using different clusters of clients in this paper

Abstract

We present a scheme for interactive ray tracing of Bezier bicubicpatches using Newton iteration in this paper. We use a mixed hi-erarchy representation as the acceleration structure. This has abounding volume hierarchy above the patches and a fixed depthsubpatch tree below it. This helps reduce the number of ray-patchintersections that needs to be evaluated and provides good initial-ization for the iterative step, keeping the memory requirements low.We use Newton iteration on the generated list of ray patch intersec-tions in parallel. Our method can exploit the cores of the CPU andthe GPU with OpenMP on the CPU and CUDA on the GPU bysharing work between them according to their relative speeds. Adata parallel framework is used throughout starting with a list ofrays, which is transformed to a list of ray-patch intersections bytraversal and then to intersections and a list of secondary rays byroot finding. Shadow and reflection rays can be handled exactly inthe same manner as a result. We also show how our method ex-tends easily to generate soft shadows using area light sources andpath tracing by tracing a large number of rays per pixel. We rendera million pixel image of the Teapot model at 125 fps on a systemwith an Intel i7 920 and a Nvidia GTX580 for primary rays onlyand at about 65 fps with one pass of shadow and refection rays.

Abstract

Displays have seen much improvements over the years, withenhancements in spatial resolution and vertical refresh, etc.,to provide better and smoother visual experiences. Color in-tensity resolution, however, has not changed much over thepast few decades. Most displays are still limited to 8-bitsper channel. Simultaneously, much work has gone into cap-turing high dynamic range images. Mapping these directlyto current displays loses information that may be critical tomany applications. We present a way to enhance intensityresolution of a given display by mixing intensities over spa-tial or temporal domains. Our system sacrifices high verticalrefresh and spatial resolution in order to gain intensity res-olution. We present three ways to mix intensities: spatially,temporally and spatio-temporally. The systems produce in-between-intensities not present on the base display, whichare clearly distinguishable by the naked eye. We evaluateour systems using both a camera and human subjects, eval-uating whether they scale the intensity resolution and alsoensuring that the newly generated intensities follow the dis-play model

Abstract

Browsers of personal digital photographs all essentially fol-low the slide show paradigm, sequencing through the pho-tos in the order they are taken. A more engaging way tobrowse personal photographs, especially of a large space likea popular monument, should involve the geometric contextof the space. In this paper, we present ageometry directedphoto browserthat enables users to browse their personalpictures with the underlying geometry of the space to guidethe process. The browser uses a pre-computed package ofgeometric information about the monument for this task.The package is used to register a set of photographs takenby the user with the common geometric space of the monu-ment. This involves localizing the images to the monumentspace by computing the camera matrix corresponding to it.We use a state-of-the-art method for fast localization. Reg-istered photographs can be browsed using a visualizationmodule that shows them in the proper geometric contextwith respect to a point-based 3D model of the monument.We present the design of the geometry-directed browser anddemonstrate its utility for a few sequences of personal im-ages of well-known monuments. We believe personal photobrowsers can provide an enhanced sense of one’s own ex-perience with a monument using the underlying geometriccontext of the monument.

Abstract

Graphics processing units (GPUs) provide large computational power at a very low price, which position GPUs well as an ubiquitous accelerator. However, GPUs are space constrained, and hence applications developed for GPUs are space sensitive. Space-constrained computational devices such as GPUs can greatly benefit from representations that reduce space consumption drastically. One such representation is the succinct representation of trees. Succinct representation of trees generally allows for operations such as parent queries, least common ancestor queries, and so on. Mapping such a robust representation to the GPU for targeted applications can lead to substantial improvement in problem sizes that are processed at a given point of time. Space-saving methods such as succinct data structures remain largely unexplored on the GPU. In this work, a succinct representation of ordered trees on the GPU is explored, with application to discrete range searching (DRS). Based on the succinct representations found applicable, a space--saving solution for DRS is presented here. In our method, DRS is mapped to a least common ancestor query on a Cartesian tree. For space-efficient DRS queries, we store the succinct representation of the Cartesian tree of an array. Our method uses a maximum of 7.5 bits of additional space per element. Furthermore, the speed-up achieved by our method is in the range of 20--25 for preprocessing and 25--35 for batch querying over a sequential implementation. Compared to an 8-threaded implementation, our preprocessing and querying methods obtain a speed-up of 6--8. We also study the applications of the DRS on the GPU. Efficient primitives expand the range of applications performed on the GPU. DRS is one such primitive with direct applications to string processing, document and text retrieval systems, and least common ancestor queries. We suggest that graph algorithms that use the least common ancestor, can be enabled on the GPU based on DRS primitive. We also show some applications of DRS in tree queries and string querying.

Abstract

Advances in cameras and web technology have madeit easy to capture and share large amounts of video data over toa large number of people. A large number of cameras overseepublic and semi-public spaces today. These raise concerns on theunintentional and unwarranted invasion of the privacy of individ-uals caught in the videos. To address these concerns, automatedmethods tode-identifyindividuals in these videos are necessary.De-identification does not aim at destroying all informationinvolving the individuals. Its ideal goals are to obscure the identityof the actor without obscuring the action. This paper outlinesthe scenarios in which de-identification is required and the issuesbrought out by those. We also present an approach to de-identifyindividuals from videos. Our approach involves tracking andsegmenting individuals in a conservative voxel space involvingx, y,and time. A de-identification transformation is applied perframe using these voxels to obscure the identity. Face, silhouette,gait, and other characteristics need to be obscured, ideally. Weshow results of our scheme on a number of videos and forseveral variations of the transformations. We present the resultsof applying algorithmic identification on the transformed videos.We also present the results of a user-study to evaluate how wellhumans can identify individuals from the transformed videos

Abstract

Raytracing dynamic scenes at interactive rates have received a lot of attention recently. We present a few strategies forhigh performance raytracing on a commodity GPU. The construction of grids needs sorting, which is fast on today’s GPUs. The grid isthus the acceleration structure of choice for dynamic scenes as per-frame rebuilding is required. We advocate the use of appropriatedata structures for each stage of raytracing, resulting in multiple structure building per frame. A perspective grid built for the cameraachieves perfect coherence for primary rays. A perspective grid built with respect to each light source provides the best performancefor shadow rays. Spherical grids handle lights positioned inside the model space and handle spotlights. Uniform grids are best forreflection and refraction rays with little coherence. We propose an Enforced Coherence method to bring coherence to them byrearranging the ray to voxel mapping using sorting. This gives the best performance on GPUs with only user-managed caches. Wealso propose a simple, Independent Voxel Walk method, which performs best by taking advantage of the L1 and L2 caches on recentGPUs. We achieve over 10 fps of total rendering on the Conference model with one light source and one reflection bounce, whilerebuilding the data structure for each stage. Ideas presented here are likely to give high performance on the future GPUs as well asother manycore architectures

Abstract

We propose an object centric representation for easy and in-tuitive navigation and manipulation of videos. Object centricrepresentation allows a user to directly access and process ob-jects as basic video components. We demonstrate a trajectorybased interface and example operations, which allow users toretime, reorder, remove or clone video objects in a ‘click anddrag’ fashion. This interface is created by extracting objectmotion information from the video. We use object detectionand tracking to obtain spatiotemporal video object tube. Thecorresponding object motion trajectories are represented in a3D(x,y,t)grid. Users can navigate and manipulate videoobjects by scrubbing or manipulating corresponding trajecto-ries. We show some example applications of proposed inter-face like object synchronization, saliency magnification, vi-sual effects and composite video creation.

Abstract

Video data is increasing rapidly along with the capacity of storage devices owned by a lay user. Users have mod­erate to large personal collections of videos and would like to keep them in an organized manner based on its content. Video organizing tools for personal users are way behind even the primitive image organizing tools. We present a mechanism in this paper to help ordinary users organize their personal collection of videos based on categories they choose. We cluster the PHOG features extracted from se­lected key frames to form a representation for each user­selected category during the learning phase. During the organization phase, labels from a K -NN classifier on these cluster centres for each key frame are aggregated to give a label to the video while categorizing. Video processing is computationally intensive. To peiform the computationally intensive steps involved, we exploit the CPU as well as the GPU that is common even on personal systems. Effective use of the parallel hardware on the system is the only way to make the tool scale reasonably to large collections that will be available soon. Our tool is able to organize a set of 100 sport videos of total duration of 1375 minutes in about 9.5 minutes. The process of learning the categories from 12 annotated videos of duration 165 minutes took 75 seconds on a GTX 580 card. These were on a standard desktop with an off-the-shelfGPU. The labeling accuracy is about 96% on all video

Abstract

s the complexity of 3D models used in computergraphics applications grows, there arises a need to visualize theoverall distribution of detail on them. Detail is a function ofthe amount of information present on a surface. In this paper,we present a method to quantify detail using a combination oflocal measures of curvature and density. We show that detailcan be used for applications like ordering for mesh decimation,visualizing abnormalities in a mesh and so on