M. Sarim, A. Hilton, Jean-Yves Guillemaut, Hansung Kim, T. Takai
{"title":"Multiple View Wide-Baseline Trimap Propagation for Natural Video Matting","authors":"M. Sarim, A. Hilton, Jean-Yves Guillemaut, Hansung Kim, T. Takai","doi":"10.1109/CVMP.2010.18","DOIUrl":"https://doi.org/10.1109/CVMP.2010.18","url":null,"abstract":"This paper presents a method to estimate alpha mattes for video sequences of the same foreground scene from wide-baseline views given sparse key-frame trimaps in a single view. A statistical inference framework is introduced for spatio-temporal propagation of high-confidence trimap labels between video sequences without a requirement for correspondence or camera calibration and motion estimation. Multiple view trimap propagation integrates appearance information between views and over time to achieve robust labelling in the presence of shadows, changes in appearance with view point and overlap between foreground and background appearance. Results demonstrate that trimaps are sufficiently accurate to allow high-quality video matting using existing single view natural image matting algorithms. Quantitative evaluation against ground-truth demonstrates that the approach achieves accurate matte estimation for camera views separated by up to 180°, with the same amount of manual interaction required for conventional single view video matting","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126199613","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":"Stereo Matching Optimization by Means of Texture Analysis","authors":"D. Tytgat, S. Lievens, Erwin Six","doi":"10.1109/CVMP.2010.19","DOIUrl":"https://doi.org/10.1109/CVMP.2010.19","url":null,"abstract":"The extraction of disparity data by means of stereo matching has well known issues in regions of low texture. This paper proposes a method which employs texture classification metrics in order to make predictions on the quality of the stereo matching output. Such predictions can then be used to alter the way the disparity data is used in further processing, or to even cancel processing of a pixel when the predicted quality is too low. Three metrics (based on laws, entropy and energy) are evaluated to this purpose on two stereo matching algorithms.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126093465","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}
C. Lipski, C. Linz, T. Neumann, M. Wacker, M. Magnor
{"title":"High Resolution Image Correspondences for Video Post-Production","authors":"C. Lipski, C. Linz, T. Neumann, M. Wacker, M. Magnor","doi":"10.1109/CVMP.2010.12","DOIUrl":"https://doi.org/10.1109/CVMP.2010.12","url":null,"abstract":"We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization. While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression can cope with high-resolution data. The incorporation of SIFT features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically in paint these regions.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134136848","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}
C. Kurz, Tobias Ritschel, E. Eisemann, Thorsten Thormahlen, H. Seidel
{"title":"Camera Motion Style Transfer","authors":"C. Kurz, Tobias Ritschel, E. Eisemann, Thorsten Thormahlen, H. Seidel","doi":"10.1109/CVMP.2010.9","DOIUrl":"https://doi.org/10.1109/CVMP.2010.9","url":null,"abstract":"When depicting both virtual and physical worlds, the viewer's impression of presence in these worlds is strongly linked to camera motion. Plausible and artist-controlled camera movement can substantially increase scene immersion. While physical camera motion exhibits subtle details of position, rotation, and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133332514","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}
R. Gherardi, R. Toldo, M. Farenzena, Andrea Fusiello
{"title":"Samantha: Towards Automatic Image-Based Model Acquisition","authors":"R. Gherardi, R. Toldo, M. Farenzena, Andrea Fusiello","doi":"10.1109/CVMP.2010.27","DOIUrl":"https://doi.org/10.1109/CVMP.2010.27","url":null,"abstract":"In this paper we describe SAMANTHA, a Structure and Motion pipeline from images which is both more robust and computationally cheaper than current competing approaches. Pictures are organized into a hierarchical tree which has single images as leaves and partial reconstructions as internal nodes. The method proceeds bottom up until it reaches the root node, corresponding to the final result. This framework is one order of magnitude faster than sequential approaches, inherently parallel, less sensitive to the error accumulation causing drift and truly uncalibrated, not needing EXIF metadata to be present in pictures. We have verified the quality of our reconstructions both qualitatively producing compelling point clouds and quantitatively, comparing them with laser scans serving as ground truth. We also show how to automatically extract a meaningful collection of planar patches obtaining a compact, stable representation of scenes.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116822354","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":"Helium3D: A Laser-Based 3D Display with '3D+' Capability","authors":"R. S. Brar, P. Surman, I. Sexton, K. Hopf","doi":"10.1109/CVMP.2010.23","DOIUrl":"https://doi.org/10.1109/CVMP.2010.23","url":null,"abstract":"In this paper we describe our latest research into 3D displays that do not require the wearing of special glasses (autostereoscopic), can provide 3D to several viewers who have a large degree of freedom of movement and direct a different image to every eye in the viewing field so that motion parallax (the ability to ‘look-around’ objects) and other interesting modes of operation are achieved (‘3D+’). The display operates by providing regions in the viewing field, referred to as exit pupils that follow the positions of the viewers’ eyes under the control of a multi-user head tracker. The display incorporates an RGB laser illumination source that illuminates a light engine. Light directions are controlled by a spatial light modulator and a front screen assembly incorporates a novel Gabor superlens. The principle of operation is explained and the construction of three iterations of the display is described.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124090247","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}
A. Evans, J. Agenjo, E. Gonzales, Sergi Gonzales, M. Dematei, M. Romeo, J. Blat
{"title":"Thinking about 3D-design Constraints for Effective 3D Interfaces","authors":"A. Evans, J. Agenjo, E. Gonzales, Sergi Gonzales, M. Dematei, M. Romeo, J. Blat","doi":"10.1109/CVMP.2010.24","DOIUrl":"https://doi.org/10.1109/CVMP.2010.24","url":null,"abstract":"Understanding the design of 3D graphical user interfaces is not as simple as doing so for their 2D counterparts. While 3D naturally has an extra dimension in which to display graphics, and thus has the potential to increase the accessible area in which information can be presented to the user, 3D also presents entirely new ways to impede user performance and increase disorientation. As a result, 3D interfaces have had mixed success since their introduction. In this paper, we critically discuss the evolution of the 3D interface, in both the academic and commercial fields. This leads us highlight the four most relevant human computer interaction (HCI) design constraints for the effective implementation of 3D interfaces. We then present an example application designed with these constraints in mind, and focused on the specific use case of visualising simple metadata in post-production.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114472688","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}
W. Bailer, Hannes Fassold, Felix Lee, Jakub Rosner
{"title":"Tracking and Clustering Salient Features in Image Sequences","authors":"W. Bailer, Hannes Fassold, Felix Lee, Jakub Rosner","doi":"10.1109/CVMP.2010.10","DOIUrl":"https://doi.org/10.1109/CVMP.2010.10","url":null,"abstract":"Many applications in media production need information about moving objects in the scene, e.g. insertion of computer-generated objects, association of sound sources to these objects or visualization of object trajectories in broadcasting. We present a GPU accelerated approach for detecting and tracking salient features in image sequences and we propose an algorithm for clustering the obtained feature point trajectories in order to obtain a motion segmentation of the set of feature trajectories. Evaluation results for both the tracking and clustering steps are presented. Finally we discuss the application of the proposed approach for associating audio sources to objects to support audio rendering for virtual sets.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129957428","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":"A Comprehensive Infrastructure and Workflow for Acquisition of High-Resolution Multi-view Content","authors":"W. Bailer, Christian Schober, Thomas Brune","doi":"10.1109/CVMP.2010.11","DOIUrl":"https://doi.org/10.1109/CVMP.2010.11","url":null,"abstract":"The current success of immersive 3D experiences in feature films and the trend towards 3D TV require advanced tools and workflows for high-quality capture of multi-view live scenes including depth information. These requirements are not fulfilled by today’s capture workflows and infrastructures based on legacy technology from 2D capture solutions. We propose a comprehensive infrastructure for capture of multi-view content supporting different methods to obtain depth information. The paper describes a device for field capture and tools for online and offline content analysis and browsing of the captured content that have been integrated into the proposed infrastructure.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124528319","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":"Prominence Driven Character Animation","authors":"C. Cullen, P. McGloin, Anna Deegan, E. McCarthy","doi":"10.1109/CVMP.2010.28","DOIUrl":"https://doi.org/10.1109/CVMP.2010.28","url":null,"abstract":"This paper details the development of a fully automated system for character animation implemented in Autodesk Maya. The system uses prioritised speech events to algorithmically generate head, body, arms and leg movements alongside eyeblinks, eyebrow movements and lip-synching. In addition, gaze tracking is also generated automatically relative to the definition of focus objects- contextually important objects in the character’s worldview. The plugin uses an animation profile to store the relevant controllers and movements for a specific character, allowing any character to run with the system. Once a profile has been created, an audio file can be loaded and animated with a single button click. The average time to animate is between 2-3 minutes for 1 minute of speech, and the plugin can be used either as a first pass system for high quality work or as part of a batch animation workflow for larger amounts of content as exemplified in television and online dissemination channels.","PeriodicalId":124181,"journal":{"name":"2010 Conference on Visual Media Production","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114646325","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}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
