L. Nyland, David K. McAllister, V. Popescu, Chris McCue, A. Lastra, Paul Rademacher, Manuel Oliveira, Gary Bishop, Gopi Meenakshisundaram, Matt Cutts, H. Fuchs
{"title":"The impact of dense range data on computer graphics","authors":"L. Nyland, David K. McAllister, V. Popescu, Chris McCue, A. Lastra, Paul Rademacher, Manuel Oliveira, Gary Bishop, Gopi Meenakshisundaram, Matt Cutts, H. Fuchs","doi":"10.1109/MVIEW.1999.781077","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781077","url":null,"abstract":"The ability to quickly acquire dense range data of familiar environments has been met with enthusiastic response in our graphics laboratory. We describe our prototype range collection system, based on a scanning laser rangefinder and a high-resolution digital color camera, that allows us to create panoramic color photographs where every pixel has an accurate range value. To accommodate occlusions, the data acquisition process is repeated from multiple locations and the results are registered with software. We discuss the acquisition system and review how the data from this prototype system have been used in existing graphics projects. We speculate about future improvements to range acquisition hardware and how those improvements impact graphics applications. The data acquired from our system is just a hint of what will be available in the future and we conclude with speculation about the impact of such data on graphics hardware and algorithms, since prevailing graphics hardware and software do not support this data well.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121146861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Synthesis and recognition of biological motion patterns based on linear superposition of prototypical motion sequences","authors":"Martin A. Giese, T. Poggio","doi":"10.1109/MVIEW.1999.781085","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781085","url":null,"abstract":"The linear combination of prototypical views has been shown to provide a powerful method for the recognition and analysis of images of three-dimensional stationary objects. We present preliminary results on an extension of this idea to video sequences. For this extension, the computation of correspondences in space-time turns out to be the central theoretical problem, which we solve with a new correspondence algorithm. Using simulated images of biological motion we demonstrate the usefulness of the superposition of prototypical sequences for the synthesis of new video sequences, and for the analysis and recognition of actions. Our method permits to impose a topology over the space of video sequences of action patterns. This topology is more complicated than a linear space. We present a new method that is based on the structural risk minimization principle of statistical learning theory, which permits to exploit this knowledge about the topology of the pattern space for recognition.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126502152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Calibrating a multi-camera system for 3D modelling","authors":"C. Wiles, A. Davison","doi":"10.1109/MVIEW.1999.781080","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781080","url":null,"abstract":"We describe a simple and novel way for calibrating the position and internal camera parameters of a camera viewing a scene with no prior knowledge of the camera being necessary. Only two views of a simple planar grid of spots are used to accurately determine the relative position of each camera in a multiple camera system. A multiple camera system is necessary for modelling dynamic objects (such as people). When the shape of the object is continually changing a large number of images must be taken simultaneously. The multiple camera system is also an important research tool allowing surface generation algorithms to be investigated under known accuracy in the camera positions. We have evaluated our algorithm's performance using simulations to determine the limits on the accuracy of our system and have demonstrated the performance in practice by producing 3D models from a four camera system.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125816861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multi-view 3D estimation and applications to match move","authors":"H. Sawhney, Y. Guo, J. Asmuth, R. Kumar","doi":"10.1109/MVIEW.1999.781079","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781079","url":null,"abstract":"Multiple views of a rigid 3D scene captured from a moving camera can be used to estimate the 3D poses (rotations and translations) and the 3D structure of the unmodeled scene. In this problem domain, there are two key problems addressed in this paper: automatic Euclidean pose estimation in extended sequences even when views of the scene rapidly change, that is features come in and go out of view relatively rapidly; and insertion of synthetic 3D objects in the real scene and their authentic projection into the given real views (also called match move). The paper presents a number of examples of different camera motions to highlight the versatility of 3D estimation. Examples of match move are also presented.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126846609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The linear geo-photometric constraint for image matching, structure reconstruction, image synthesis and object recognition","authors":"Gang Xu, Guodong Guo","doi":"10.1109/MVIEW.1999.781083","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781083","url":null,"abstract":"We show that under orthographic projection (can be relaxed to weak perspective, or scaled orthographic projection) and with a fixed camera and fixed light sources, the images of a moving Lambertian surface can be modelled as a linear combination of three distinct images, with identical coefficients for both shape and intensity. We call this the linear geo-photometric constraint. Using this new constraint, we can match images, reconstruct structure, synthesize new images and recognize objects. Experimental results are shown.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116227690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Illumination-based image synthesis: creating novel images of human faces under differing pose and lighting","authors":"A. Georghiades, P. Belhumeur, D. Kriegman","doi":"10.1109/MVIEW.1999.781082","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781082","url":null,"abstract":"We present an illumination-based method for synthesizing images of an object under novel viewing conditions. Our method requires as few as three images of the object taken under variable illumination, but from a fixed viewpoint. Unlike multi-view based image synthesis, our method does not require the determination of point or line correspondences. Furthermore, our method is able to synthesize not simply novel viewpoints, but novel illumination conditions as well. We demonstrate the effectiveness of our approach by generating synthetic images of human faces.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117092467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Real-time rendering system of moving objects","authors":"Y. Kunita, M. Inami, T. Maeda, S. Tachi","doi":"10.1109/MVIEW.1999.781086","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781086","url":null,"abstract":"We have been developing a system named \"mutual tele-existence\" which allows for face-to-face communication between remote users (Tachi et al., 1996). Although image-based rendering (IBR) is suitable for rendering human figures with a complex geometry, conventional IBR techniques cannot readily be applied to our system. Because most IBR techniques include time-consuming processes, they cannot capture the source images and simultaneously render the destination images. In this paper, we propose a novel method focusing on real-time rendering. Moreover, we introduce equivalent depth of field to measure the fidelity of the synthesized image. If the object is in this range, accurate rendering is guaranteed. Then, we introduce a prototype machine that has 12 synchronized cameras on the linear actuator. Finally, we present some experimental results of our prototype machine.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115561731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Rendering articulated figures from examples","authors":"Trevor Darrell","doi":"10.1109/MVIEW.1999.781084","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781084","url":null,"abstract":"This paper presents new methods to robustly track and interpolate images of complex articulated figures. Traditional interpolation approaches fail on these cases since appearance is not necessarily a smooth function nor a linear manifold. We show how to model such appearance mappings with sets of examples which are each smooth functions. These well-behaved groups can cover overlapping regions of parameter space, and are empirically validated. A set growing procedure is used to find example clusters which are well-approximated within their convex hull; interpolation then proceeds only within a single such set. With this method physically valid images are produced even in regions of parameter space where the overall mapping is singular and nearby examples have different appearances. Our analysis stage tracks the occluding boundaries of articulated figures, even when there is no foreground contrast on an individual limb. Results generating both simulated and real arm images are demonstrated.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125371088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Gauge invariance in projective 3D reconstruction","authors":"P. McLauchlan","doi":"10.1109/MVIEW.1999.781081","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781081","url":null,"abstract":"Bundle adjustment is a standard photogrammetric technique for optimizing the 3D reconstruction of a scene from multiple images. There is an inherent gauge (coordinate frame) ambiguity in 3D reconstruction that can seriously affect the convergence of bundle adjustment algorithms. We address this issue and show that a simple pre-conditioning step removes the effect of the choice of coordinate frame, and together with a set of enforced constraints on the reconstruction, achieves along with this invariance greatly increased convergence speed over existing methods. The new approach applies to all the well-known 3D reconstruction models: projective, affine and Euclidean. We develop the idea for projective reconstruction. The normalization stage partially removes the gauge freedom, reducing the coordinate frame choice from a general 3D homography to an orthogonal transformation; then constraints are incorporated in the bundle adjustment iterations that enforce the normalisation condition to first order. In the projective case the approach relies on a currently unproven matrix conjecture, which we nevertheless strongly believe to be correct, based on extensive experimental evidence.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129305416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Object modeling using tomography and photography","authors":"David T. Gering, William M. Wells","doi":"10.1109/MVIEW.1999.781078","DOIUrl":"https://doi.org/10.1109/MVIEW.1999.781078","url":null,"abstract":"This paper explores techniques for constructing a 3D computer model of an object from the real world by applying tomographic methods to a sequence of photographic images. While some existing methods can better handle occlusion and concavities, the techniques proposed have the advantageous capability of generating very high-resolution models with attractive speed and simplicity. The application of these methods is presently limited to an appropriate class of mostly convex objects with Lambertian surfaces. The results are volume rendered or surface rendered to produce an interactive display of the object with near life-like realism.","PeriodicalId":341337,"journal":{"name":"Proceedings IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes (MVIEW'99)","volume":"06 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127370878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}