Evren Imre
Research Subjects
Evren Imre has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Abdullah Aydın Alatan
Middle East Technical University
5 shared publications - Adrian Hilton
Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK
5 shared publications - Sebastian Knorr
Hochschule für Technik und Wirtschaft Berlin, Berlin, Germany
4 shared publications - Uğur Güdükbay
Department of Computer Engineering, Bilkent University, Ankara, Turkey
4 shared publications - Jean-Yves Guillemaut
University of Surrey, Guildford, United Kingdom
3 shared publications - Thomas Sikora
Communication Systems Group Technische Universität Berlin
2 shared publications
Latest Publications
- 27 February 2021
- Published by Springer Nature
- p. 71-88
Multi-view Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People
- 27 February 2021
- Published by Springer Nature
- p. 71-88
Multi-view Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
IMPART: Big media data processing and analysis for film production
A typical high-end film production generates several terabytes of data per day, either as footage from multiple cameras or as background information regarding the set (laser scans, spherical captures, etc). The EU project IMPART (impart.upf.edu) has been researching solutions that improve the integration and understanding of the quality of the multiple data sources to support creative decisions onset or near it, and an enhanced post-production as well. The main results covered in this paper are: a public multisource production dataset made available for research purposes, monitoring and quality assurance of multicamera set-ups, multisource registration, anthropocentric visual analysis for semantic content annotation, acceleration of 3D reconstruction, and integrated 2D–3D web visualization tools.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
IMPART: Big media data processing and analysis for film production
A typical high-end film production generates several terabytes of data per day, either as footage from multiple cameras or as background information regarding the set (laser scans, spherical captures, etc). The EU project IMPART (impart.upf.edu) has been researching solutions that improve the integration and understanding of the quality of the multiple data sources to support creative decisions onset or near it, and an enhanced post-production as well. The main results covered in this paper are: a public multisource production dataset made available for research purposes, monitoring and quality assurance of multicamera set-ups, multisource registration, anthropocentric visual analysis for semantic content annotation, acceleration of 3D reconstruction, and integrated 2D–3D web visualization tools.
- 1 October 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15506185,p. 395-402
Through-the-Lens Multi-camera Synchronisation and Frame-Drop Detection for 3D Reconstruction
Synchronisation is an essential requirement for multiview 3D reconstruction of dynamic scenes. However, the use of HD cameras and large set-ups put a considerable stress on hardware and cause frame drops, which is usually detected by manually verifying very large amounts of data. This paper improves [9], and extends it with frame-drop detection capability. In order to spot frame-drop events, the algorithm fits a broken line to the frame index correspondences for each camera pair, and then fuses the pair wise drop hypotheses into a consistent, absolute frame-drop estimate. The success and the practical utility of the the improved pipeline is demonstrated through a number of experiments, including 3D reconstruction and free-viewpoint video rendering tasks.
- 1 October 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15506185,p. 395-402
Through-the-Lens Multi-camera Synchronisation and Frame-Drop Detection for 3D Reconstruction
Synchronisation is an essential requirement for multiview 3D reconstruction of dynamic scenes. However, the use of HD cameras and large set-ups put a considerable stress on hardware and cause frame drops, which is usually detected by manually verifying very large amounts of data. This paper improves [9], and extends it with frame-drop detection capability. In order to spot frame-drop events, the algorithm fits a broken line to the frame index correspondences for each camera pair, and then fuses the pair wise drop hypotheses into a consistent, absolute frame-drop estimate. The success and the practical utility of the the improved pipeline is demonstrated through a number of experiments, including 3D reconstruction and free-viewpoint video rendering tasks.
- 1 May 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15506185,p. 260-267
Calibration of Nodal and Free-Moving Cameras in Dynamic Scenes for Post-Production
In film production, many post-production tasks require the availability of accurate camera calibration information. This paper presents an algorithm for through-the-lens calibration of a moving camera for a common scenario in film production and broadcasting: The camera views a dynamic scene, which is also viewed by a set of static cameras with known calibration. The proposed method involves the construction of a sparse scene model from the static cameras, with respect to which the moving camera is registered, by applying the appropriate perspective-n-point (PnP) solver. In addition to the general motion case, the algorithm can handle the nodal cameras with unknown focal length via a novel P2P algorithm. The approach can identify a subset of static cameras that are more likely to generate a high number of scene-image correspondences, and can robustly deal with dynamic scenes. Our target applications include dense 3D reconstruction, stereoscopic 3D rendering and 3D scene augmentation, through which the success of the algorithm is demonstrated experimentally.
- 1 May 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15506185,p. 260-267
Calibration of Nodal and Free-Moving Cameras in Dynamic Scenes for Post-Production
In film production, many post-production tasks require the availability of accurate camera calibration information. This paper presents an algorithm for through-the-lens calibration of a moving camera for a common scenario in film production and broadcasting: The camera views a dynamic scene, which is also viewed by a set of static cameras with known calibration. The proposed method involves the construction of a sparse scene model from the static cameras, with respect to which the moving camera is registered, by applying the appropriate perspective-n-point (PnP) solver. In addition to the general motion case, the algorithm can handle the nodal cameras with unknown focal length via a novel P2P algorithm. The approach can identify a subset of static cameras that are more likely to generate a high number of scene-image correspondences, and can robustly deal with dynamic scenes. Our target applications include dense 3D reconstruction, stereoscopic 3D rendering and 3D scene augmentation, through which the success of the algorithm is demonstrated experimentally.
- 1 January 2010
- Published by British Machine Vision Association and Society for Pattern Recognition
- p. 1-12
Moving Camera Registration for Multiple Camera Setups in Dynamic Scenes
Many practical applications require an accurate knowledge of the extrinsic calibration (\ie, pose) of a moving camera. The existing SLAM and structure-from-motion solutions are not robust to scenes with large dynamic objects, and do not fully utilize the available information in the presence of static cameras, a common practical scenario. In this paper, we propose an algorithm that addresses both of these issues for a hybrid static-moving camera setup. The algorithm uses the static cameras to build a sparse 3D model of the scene, with respect to which the pose of the moving camera is estimated at each time instant. The performance of the algorithm is studied through extensive experiments that cover a wide range of applications, and is shown to be satisfactory
- 1 January 2010
- Published by British Machine Vision Association and Society for Pattern Recognition
- p. 1-12
Moving Camera Registration for Multiple Camera Setups in Dynamic Scenes
Many practical applications require an accurate knowledge of the extrinsic calibration (\ie, pose) of a moving camera. The existing SLAM and structure-from-motion solutions are not robust to scenes with large dynamic objects, and do not fully utilize the available information in the presence of static cameras, a common practical scenario. In this paper, we propose an algorithm that addresses both of these issues for a hybrid static-moving camera setup. The algorithm uses the static cameras to build a sparse 3D model of the scene, with respect to which the pose of the moving camera is estimated at each time instant. The performance of the algorithm is studied through extensive experiments that cover a wide range of applications, and is shown to be satisfactory
- 1 May 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 381-386
Improved inverse-depth parameterization for monocular simultaneous localization and mapping
Inverse-depth parameterization can successfully deal with the feature initialization problem in monocular simultaneous localization and mapping applications. However, it is redundant, and when multiple landmarks are initialized from the same image, it fails to enforce the ldquocommon originrdquo constraint. The authors propose two new variants that addresses both of these issues. The experimental results indicate that the proposed approach achieves a better performance at a lower computational cost.
- 1 May 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 381-386
Improved inverse-depth parameterization for monocular simultaneous localization and mapping
Inverse-depth parameterization can successfully deal with the feature initialization problem in monocular simultaneous localization and mapping applications. However, it is redundant, and when multiple landmarks are initialized from the same image, it fails to enforce the ldquocommon originrdquo constraint. The authors propose two new variants that addresses both of these issues. The experimental results indicate that the proposed approach achieves a better performance at a lower computational cost.
- 20 January 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 18 (3) , 483-494
Rate-Distortion Efficient Piecewise Planar 3-D Scene Representation From 2-D Images
In any practical application of the 2-D-to-3-D conversion that involves storage and transmission, representation efficiency has an undisputable importance that is not reflected in the attention the topic received. In order to address this problem, a novel algorithm, which yields efficient 3-D representations in the rate distortion sense, is proposed. The algorithm utilizes two views of a scene to build a mesh-based representation incrementally, via adding new vertices, while minimizing a distortion measure. The experimental results indicate that, in scenes that can be approximated by planes, the proposed algorithm is superior to the dense depth map and, in some practical situations, to the block motion vector-based representations in the rate-distortion sense.
- 20 January 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 18 (3) , 483-494
Rate-Distortion Efficient Piecewise Planar 3-D Scene Representation From 2-D Images
In any practical application of the 2-D-to-3-D conversion that involves storage and transmission, representation efficiency has an undisputable importance that is not reflected in the attention the topic received. In order to address this problem, a novel algorithm, which yields efficient 3-D representations in the rate distortion sense, is proposed. The algorithm utilizes two views of a scene to build a mesh-based representation incrementally, via adding new vertices, while minimizing a distortion measure. The experimental results indicate that, in scenes that can be approximated by planes, the proposed algorithm is superior to the dense depth map and, in some practical situations, to the block motion vector-based representations in the rate-distortion sense.
- 1 January 2009
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 1-10
A 3-Component Inverse Depth Parameterization for Particle Filter SLAM
- 1 January 2009
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 1-10
A 3-Component Inverse Depth Parameterization for Particle Filter SLAM
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Rate-Distortion Guided Piecewise Planar 3D Scene Representation
This paper proposes a novel 3D piecewise planar reconstruction algorithm, which utilizes the statistical error between a particular frame and its prediction to refine a coarse 3D piecewise planar representation. The algorithm aims utilization of 3D scene geometry to remove the visual redundancy between frame pairs in any predictive coding scheme. This approach associates the rate increase with the quality of representation for determining an efficient description for a given budget. The preliminary experiments on synthetic and real data indicate the validity of the rate-distortion based approach.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Rate-Distortion Guided Piecewise Planar 3D Scene Representation
This paper proposes a novel 3D piecewise planar reconstruction algorithm, which utilizes the statistical error between a particular frame and its prediction to refine a coarse 3D piecewise planar representation. The algorithm aims utilization of 3D scene geometry to remove the visual redundancy between frame pairs in any predictive coding scheme. This approach associates the rate increase with the quality of representation for determining an efficient description for a given budget. The preliminary experiments on synthetic and real data indicate the validity of the rate-distortion based approach.
- 1 May 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Piecewise-Planar 3D Reconstruction in Rate-Distortion Sense
In this paper, a novel rate-distortion optimization inspired 3D piecewise-planar reconstruction algorithm is proposed. The algorithm refines a coarse 3D triangular mesh, by inserting vertices in a way to minimize the intensity difference between an image and its prediction. The preliminary experiments on synthetic and real data indicate the validity of the proposed approach.
- 1 May 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Piecewise-Planar 3D Reconstruction in Rate-Distortion Sense
In this paper, a novel rate-distortion optimization inspired 3D piecewise-planar reconstruction algorithm is proposed. The algorithm refines a coarse 3D triangular mesh, by inserting vertices in a way to minimize the intensity difference between an image and its prediction. The preliminary experiments on synthetic and real data indicate the validity of the proposed approach.