Abstract

In this paper, we present a new approach for object removaland video completion of indoor scenes. In indoor images, the frames arenot affine related. The region near the object to be removed can havemultiple planes with sharply different motions. Dense motion estimationmay fail for such scenes due to missing pixels. We use feature tracking tofind dominant motion between two frames. The geometry of the motionof multiple planes is used to segment the motion layers into componentplanes. The homography corresponding to each hole pixel is used to warpa frame in the future or past for filling it. We show the application ofour technique on some typical indoor videos.

Abstract

Depth Images are viable representations that can be computed from the real world using cameras and/or other scanning devices. The depth map provides 2-kD structure of the scene. A set of Depth Images can provide hole-free rendering of the scene. Multiple views need to blended to provide smooth hole-free rendering, however. Such a representation of the scene is bulky and needs good algorithms for real-time rendering and efficient representation. In this paper, we present a discussion on the Depth Image representation and provide a GPU-based algorithm that can render large models represented using DIs in real time. We then present a proxy-based compression scheme for Depth Images and provide results for the same. Results are shown on synthetic scenes under different conditions and on some scenes generated from images. Lastly, we initiate discussion on varying quality levels in IBR and show a way to create representations using DIs with different trade-offs between model size and rendering quality. This enables the use of this representation for a variety of rendering situations.

Abstract

Recording dynamic events, such as a sports event,a ballet performance, or a lecture, digitally for ex-periencing in a spatiotemporally distant setting re-quires 4D capture: three dimensions for their geom-etry/appearance over the fourth dimension of time.Cameras are suitable for this task as they are non-intrusive, universal, and inexpensive. Computer Vi-sion techniques have advanced sufficiently to make the4D capture possible. In this paper, we present a his-torical perspective on the Virtualized RealityTMsys-tem developed since early 90s to early 2000 at CMUfor the 4D capture of dynamic events

Abstract

Terrains and other geometric models have been traditionally storedlocally. Their remote access presents the characteristics that are acombination of data serving such as files and real-time streaminglike audio-visual media. In this sketch we describe a client-serversystem to serve and stream large terrains to heterogenous clients.This process is sensitive to both the client’s capabilities as well asthe available network bandwidth. Level of Detail and view predic-tion are used to alleviate the effects of changing latency and band-width. We discuss the design of a terrain streaming system andpresent preliminary results

Abstract

Image-based rendering techniques include those with geometry and those without. Geometric information in the form of a depth map aligned with the image holds a lot of promise for IBR due to the several methods available to capture it. It can improve the quality of generated views using a limited number of views. Compression of light fields or multiple images has attracted a lot of attention in the past. Compression of multiple depth maps of the same scene has not been explored much in the literature. We propose a method for compressing multiple depth maps in this paper using geometric proxy. Different quality of rendering and compression ratio can be achieved by varying different parameters. Experiments show the effectiveness of the compression technique on several model data

Abstract

The size and detail of graphics environments in everyday use has gone up considerably recently. Still, most applications use locally resident geometric content for rendering. In this paper, we present a system to stream large graphics environments from a central server to multiple number of clients. The streaming is transparent to the user who can treat remote models just like local ones. The streaming system automatically adapts to the rendering capabilities, network bandwidth and latency of the client and transmits an optimized model. We present the design of the streaming system and give results of streaming a large model using it

Abstract

Large virtual environments arise in many applications and may be used by many users simultaneously for walkthroughs. It is not feasible to store a copy of the whole environment at each of the client locations due to their size. The dynamic nature of the environment also makes it more convenient for a central server to ensure consistency across different users. In this paper, we present a client-server based system for visualizing large environments from remote users. The client gets only the portion of the geometry necessary for navigating around the current user location. The system can adapt to different client parameters such as graphics capability, network bandwidth, communication latency, etc. We present the design and implementation of the system in this paper and produce relevant results using it

Abstract

Graphics models for virtual environments are increasingly getting massive, requiring large amounts of memory to store and high end graphics capabilities to render. It may not be possible or desirable to store the entire model in the station where it will be rendered, especially for environments that change. Such virtual models could be stored on a server and streamed to remote clients on demand. In this paper, we present the design and implementation of a client-server system to render large virtual environments. Our system can provide the best visualization quality for a wide range in connection bandwidth and latency and the rendering capacity of the client. The system uses a visibility-based geometry representation so that little invisible geometry is sent to the client. Incremental updating and client-side prediction of user motion optimize the communication requiremnts for a given client. We present results of the study conducted on a representative range of the relevant parameters in this paper

Abstract

Image Based Rendering holds a lot of promise for navigating through a real world scene without modeling it manually. Different representations have been proposed for IBR in the literature. In this paper, we argue that a representation using depth maps and texture images from a number of viewpoints is a rich and viable representation for IBR. We discuss different aspects of this representation including capture, representation, compression and rendering. We show several results to show how the representation can be used to model and render complex scenes.

Abstract

Recognition of planar shapes is an important problem in computer vision andpattern recognition. The same planar object contour imaged from di1erent cameras or from di1erent viewpoints looks di1erent and their recognition is non-trivial. Traditional shape recognition deals with views of the shapes that di1er only by simple rotations, translations, and scaling. However, shapes su1er more serious deformation between two general views and hence recognition approaches designed to handle translations, rotations, and/or scaling would prove to be insu5cient. Many algebraic relations between matching primitives in multiple views have been identi7edrecently. In this paper, we explore how shape properties andmultiview relations can be combinedto recognize planar shapes across multiple views. We propose novel recognition constraints that a planar shape boundary must satisfy in multiple views. The constraints are on the rank of a Fourier-domain measurement matrix computed from the points on the shape boundary. Our method can additionally compute the correspondence between the curve points after a match is established. We demonstrate the applications of these constraints experimentally on a number of synthetic and real images.