DC Field | Value | Language |
---|---|---|
dc.contributor.author | Bogdan, Oleksandr | ko |
dc.contributor.author | Eckstein, Viktor | ko |
dc.contributor.author | Rameau, Francois | ko |
dc.contributor.author | Bazin, Jean-Charles | ko |
dc.date.accessioned | 2019-01-22T08:07:45Z | - |
dc.date.available | 2019-01-22T08:07:45Z | - |
dc.date.created | 2018-12-20 | - |
dc.date.created | 2018-12-20 | - |
dc.date.created | 2018-12-20 | - |
dc.date.issued | 2018-12-13 | - |
dc.identifier.citation | 15th ACM SIGGRAPH European Conference on Visual Media Production (CVMP), pp.6:1 - 6:10 | - |
dc.identifier.uri | http://hdl.handle.net/10203/248808 | - |
dc.description.abstract | Calibration of wide field-of-view cameras is a fundamental step for numerous visual media production applications, such as 3D reconstruction, image undistortion, augmented reality and camera motion estimation. However, existing calibration methods require multiple images of a calibration pattern (typically a checkerboard), assume the presence of lines, require manual interaction and/or need an image sequence. In contrast, we present a novel fully automatic deep learning-based approach that overcomes all these limitations and works with a single image of general scenes. Our approach builds upon the recent developments in deep Convolutional Neural Networks (CNN): our network automatically estimates the intrinsic parameters of the camera (focal length and distortion parameter) from a single input image. In order to train the CNN, we leverage the great amount of omnidirectional images available on the Internet to automatically generate a large-scale dataset composed of millions of wide field-of-view images with ground truth intrinsic parameters. Experiments successfully demonstrated the quality of our results, both quantitatively and qualitatively. | - |
dc.language | English | - |
dc.publisher | ACM SIGGRAPH | - |
dc.title | DeepCalib: A Deep Learning Approach for Automatic Intrinsic Calibration of Wide Field-of-View Cameras | - |
dc.type | Conference | - |
dc.identifier.wosid | 000481980400006 | - |
dc.identifier.scopusid | 2-s2.0-85061781785 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 6:1 | - |
dc.citation.endingpage | 6:10 | - |
dc.citation.publicationname | 15th ACM SIGGRAPH European Conference on Visual Media Production (CVMP) | - |
dc.identifier.conferencecountry | UK | - |
dc.identifier.conferencelocation | BFI Southbank, London | - |
dc.identifier.doi | 10.1145/3278471.3278479 | - |
dc.contributor.localauthor | Bazin, Jean-Charles | - |
dc.contributor.nonIdAuthor | Bogdan, Oleksandr | - |
dc.contributor.nonIdAuthor | Eckstein, Viktor | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.