Abstract

The primitives of point-based representations are in-dependent but are rendered using surfels, which approxi-mate the immediate neighborhood of each point linearly.A large number of surfels are needed to convey the exactshape. Higher-order approximations of the local neigh-borhood have the potential to represent the shape usingfewer primitives,simultaneously achieving higher renderingspeeds. In this paper, we proposealgebraic splatsas abasic primitive of representation for point based models.An algebraic splat based representation can be computedusing a moving least squares procedure. We specificallystudy low order polynomial splats in this paper. Quadraticand cubic splats provide good quality and high renderingspeed using far fewer primitives on a wide range of mod-els. They can also be rendered fast using ray tracing onmodern GPUs. We also present an algorithm to constructa representation of a model with a user-specified number ofprimitives. Our method to generates a hole-free represen-tation parametrized by a smoothing radius. The hole-freerepresentation reduces the number of primitives needed bya factor 20 to 30 on most models and by a factor of over100 on dense models like David with little or no drop invisual quality. We also present a two-pass GPU algorithmthat ray-traces the algebraic splats and blends them usinga Gaussian weighting scheme for smooth appearance. Weare able to render models like David at upwards of 200 fpson a commodity GPU using algebraic splats.

Abstract

We present a non-photo realistic, real-time painterly ren-dering technique for terrains. The painterly appearanceand the impression of terrains is created by effectively ren-dering several brush strokes. The strokes have fixed loca-tions on the surfaces of the terrain during animation to en-able frame to frame coherency. The strokes are rendered asalpha blended sprites in two-dimensions and are orientedalong the slope of terrain analogous to the way artists painton canvas. By exploiting the regular nature of terrain data,we create pre-decided rendering depth orders for primitivesfor any camera orientation.With this, we avoid the neces-sity of sorting the primitives of sprites required for alphablending. We use DirectX10/SM4.0 based shaders to renderstrokes to improve performance. Being distributed on ter-rain, strokes get cluttered when they are closely located onscreen. We follow a level of detail scheme that maintains auniform stroke density in screen space. Various styles canbe achieved with different stroke variations. Phong shadingthe rendered output in real-time is possible for more variedstyles. We achieve painterly rendering in real-time with acombination of object space positioning and image spacerendering of strokes. We illustrate our method with imagesand performance results.

Abstract

Many events are captured using multiple cameras today. Frames of each video stream have to be synchronized and aligned to a common time axis before processing them. Synchronization of the video streams necessarily needs a hardware based solution that is applied while capturing. The alignment problem between the frames of multiple videos can be posed as a search using traditional measures for image similarity. Multiview relations and constraints developed in Computer Vision recently can provide more elegant solutions to this problem. In this paper, we provide two solutions for the video frame alignment problem using two view and three view constraints. We present solutions to this problem for the case when the videos are taken using affine cameras and for general projective cameras. Excellent experimental results are achieved by our algorithms.

Abstract

Video completion algorithms have concentrated on obtaining visually consistent solutions to fill-in the missing portions, without any emphasis on the physical correctness of the video. Resulting solutions thus use texture or image structure based cues and are limited in the situations they can handle. In this paper we take a model based signal processing approach to video completion [1]. Completion of the video is then defined as satisfying the given model by detecting and removing the error (selected parts of the video to be replaced). Given a probabilistic model, video completion then becomes an unsupervised learning algorithm with the input video giving a “noisy” version. Dense completion is the automatic inferencing of the “noise-less” or “true” video from the input. This approach finds a solution that satisfies visual coherence and is applicable to a wide variety of scenarios. We demonstrate the efficacy of our approach and its wide applicability using two scenarios.

Abstract

A video from a moving camera produces different number of observations of different scene areas. We can construct an attention map of the scene by bringing the frames to a common reference and counting the number of frames that observed each scene point. Different representations can be constructed from this. The base of the attention map gives the scene mosaic. Super-resolved images of parts of the scene can be obtained using a subset of observations or video frames. We can combine mosaicing with superresolution by using all observations, but the magnification factor will vary across the scene based on the attention received. The height of the attention map indicates the amount of super-resolution for that scene point. We modify the traditional super-resolution framework to generate a varying resolution image for panning cameras in this paper. The varying resolution image uses all useful data available in a video. We introduce the concept of attention-based super-resolution and give the modified framework for it. We also show its applicability on a few indoor and outdoor videos.

Abstract

Intermodal (IM) trains are typically the fastest freight trains operated in North America. The aerodynamic characteristics of many of these trains are often relatively poor resulting in high fuel consumption. However, considerable variation in fuel efficiency is possible depending on how the loads are placed on railcars in the train. Consequently, substantial potential fuel savings are possible if more attention is paid on the loading configurations of trains. A wayside machine vision (MV) system was developed to automatically scan passing IM trains and assess their aerodynamic efficiency. MV algorithms are used to analyse these images, detect and measure gaps between loads. In order to make use of the data, a scoring system was devel- oped based on two attributes – the aerodynamic coefficient and slot efficiency. The aerodynamic coefficient is calculated using the Aerodynamic Subroutine of the Train Energy Model. Slot effi- ciency represents the difference between the actual and ideal loading configuration given the particular set of railcars in the train. This system can provide IM terminal managers feedback on loading performance for trains and be integrated into the software support systems used for loading assignment.

Abstract

The advent of advanced graphics technologies and im-proved hardware has enabled the generation of highly com-plex models with huge number of triangles. Point-basedrepresentations and rendering have emerged as viable rep-resentations for high-quality models in this scenario. Thesemethods have been demonstrated only on high resolution,compact objects so far. They have to be adapted to environ-ments that extend over large areas to be considered seriousrepresentations. In this paper, we present an adaptation ofthe point-based representation to large, hierarchical envi-ronments. We show how point-based data can be generatedby sampling polygon-based representations. We also showthe combination of an object hierarchy and multiresolutionpoint representations and develop rendering algorithms forthe same. The multiresolution representation is constructedduring the generation process. We then show a hybrid rep-resentation in which the more complex portions of the envi-ronment are represented using points and others using theoriginal polygon-based representation. This produces bet-ter rendering performance by keeping large, flat regions astriangles. We demonstrate the method on the model of theFatehpur Sikri which has 14000 objects with over 500,000triangles

Abstract

Digitally recording dynamic events, such as sporting events, for experiencing in a spatio-temporally distant and arbitrary setting requires 4D capture: three dimensions for their geometry and appearance over the fourth dimension of time. Today's computer vision techniques make 4D capture possible. The virtualized reality system serves as an example on the general problem of digitizing dynamic events. In this article, we present the virtualized reality system's details from a historical perspective

Abstract

Cluster-based tiled display walls can provide cost-effective and scalable displays with high resolution and a large displayarea. The software to drive them needs to scale too if arbitrarily large displays are to be built. Chromium is a popular software API usedto construct such displays. Chromium transparently renders any OpenGL application to a tiled display by partitioning and sendingindividual OpenGL primitives to each client per frame. Visualization applications often deal with massive geometric data with millions ofprimitives. Transmitting them every frame results in huge network requirements that adversely affect the scalability of the system. Inthis paper, we present Garuda, a client-server-based display wall framework that uses off-the-shelf hardware and a standard network.Garuda is scalable to large tile configurations and massive environments. It can transparently render any application built using theOpen Scene Graph (OSG) API to a tiled display without any modification by the user. The Garuda server uses an object-based scenestructure represented using a scene graph. The server determines the objects visible to each display tile using a novel adaptivealgorithm that culls the scene graph to a hierarchy of frustums. Required parts of the scene graph are transmitted to the clients, whichcache them to exploit the interframe redundancy. A multicast-based protocol is used to transmit the geometry to exploit the spatialredundancy present in tiled display systems. A geometry push philosophy from the server helps keep the clients in sync with oneanother. Neither the server nor a client needs to render the entire scene, making the system suitable for interactive rendering ofmassive models. Transparent rendering is achieved by intercepting the cull, draw, and swap functions of OSG and replacing them withour own. We demonstrate the performance and scalability of the Garuda system for different configurations of display wall. We alsoshow that the server and network loads grow sublinearly with the increase in the number of tiles, which makes our scheme suitable toconstruct very large displays

Abstract

Large graphs involving millions of vertices are common in many prac-tical applications and are challenging to process. Practical-time implementationsusing high-end computers are reported but are accessible only to a few. GraphicsProcessing Units (GPUs) of today have high computation power and low price.They have a restrictive programming model and are tricky to use. The G80 lineof Nvidia GPUs can be treated as a SIMD processor array using the CUDA pro-gramming model. We present a few fundamental algorithms – including breadthfirst search, single source shortest path, and all-pairs shortest path – using CUDAon large graphs. We can compute the single source shortest path on a 10 millionvertex graph in1.5seconds using the Nvidia 8800GTX GPU costing $600. Insome cases optimal sequential algorithm is not the fastest on the GPU architec-ture. GPUs have great potential as high-performance co-processors.