Tomas
Pajdla
[Piedlah]
Assistant Professor 
Address: Karlovo namesti 13, 12135 Praha 2,  
Center for Machine
Perception Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague 

Teaching:  Computer Vision
& Intelligent
Robotics "How to" for my students, Master, Batchelor, and semestral projects (in Czech) 

Projects: 
DIRAC
Detection & Identification of Rare AudioVisual Cues, FP6 EU
FP6IST027787 BeNoGo Being There  Without Going, FP5 EU IST200139184 OMNIVIEWS Omnidirectional Visual System, FP5 EU IST199929017  
Lectures: 
Omnidirectional
Vision Course @ ICCV 2003  
Students:  Finished: T.Svoboda (PhD), M.Urban (PhD), S.Gaechter (MSc), O.Chum (MSc), R.Horcik (MSc), J.Sivic (MSc), M.Menem (MSc), B.Micusik (PhD). Current: H.Bakstein (PhD), D.Martinec (PhD), M.Havlena (PhD), T.Ehlgen (PhD), Z.Kukelova (PhD).  
Service:  PC Chair of ECCV 2004, Area Chair of ICCV 2005, BMVC 2005, ACCV 2006, CVPR 2006, BMVC 2006, PC Member of OMNIVIS workshops, Reviewer of IEEE PAMI & IJCV  
Links:  Short Curriculum Vitae, Long Curriculum Vitae, CMP spinoff Neovision Ltd.  
Publications:  
NonCentral 
T.Pajdla. Nonclassical
Ray Cameras. Technical report CTUCMP199911.
November 1999. (programme to study
noncentral cameras  mosaics, plenoptic functions, light fields 
formulated) F.Huang, T.Pajdla. Epipolar Geometry in Concentric Panoramas. Technical report CTUCMP200007, March 2000 (stereo geometry of one configuration of concentric panoramas  inspiring but not entirely correct) T.Pajdla. Epipolar Geometry of Some Nonclassical Cameras. Computer Vision Winter Workshop 2001. Bled, Slovenia. pp. 223233, February 2001. (generalized epipolar geometry implies that rays of both cameras must form opposite reguli) H.Bakstein, T.Pajdla. 3D Reconstruction from 360x360 Mosaics. CVPR 2001, pp. 7277, IEEE December 2001. (classes of reconstruction from uncalibrated 360x360 mosaic, epipolar alignment) T.Pajdla. Stereo with Oblique Cameras. Workshop on Stereo and MultiBaseline Vision, pp. 8591, IEEE December 2001. (see the following IJCV paper) J.Sivic, T.Pajdla. Geometry of Concentric Multiperspective Panoramas. Technical report CTUCMP200205. February 2002. (geometry and stereogeometry, classification of generalized epipolar geometries) T.Pajdla. Geometry of TwoSlit Camera. Technical report CTUCMP200202, March 2002. (geometry of Xslits cameras and Oblique cameras, analyzed in the complexification of P^3) T.Pajdla. Stereo with Oblique Cameras. IJCV, 47(1):161170, Kluwer May 2002. (the most noncentral camera with a generalized epipolar geometry: definitions, properties, philosophy, genaration by a collineation) H.Bakstein, T.Pajdla. Rendering Novel Views from a Set of Omnidirectional Mosaic Images. Workshop on Omnidirectional Vision and Camera Networks 2003, CD ROM, IEEE June 2003. (image beased rendering with noncentral cameras) H.Bakstein, T.Pajdla, D.Vecerka. Rendering Almost Perspective Views from a Sparse Set of Omnidirectional Images. BMVC 2003, pp. 241250, BMVA September 2003. (IBR with noncentral images  XSlits images can be scaled to look like perspective ones) D.Feldman, T. Pajdla, D.Weinshall. On the Epipolar Geometry of the CrossedSlits Projection. ICCV 2003, pp. 988995, IEEE October 2003. (stereo geometry of XSlits cameras, search curves, fundamental matrix) B.Micusik, T.Pajdla. Autocalibration & 3D Reconstruction with Noncentral Catadioptric Cameras . CVPR 2004, Washington US, June 2004. (autocalibration of noncentral quadric catadioptric cameras by epipolar geometry estimation, worked out for parbolic, hyperbolic, and spherical mirrors.) M.Menem, T.Pajdla.Constraints on Perspective Images and Circular Panoramas. BMVC 2004, BMVA, September 2004. (formutalion and estimation of the multiview constrint for the mixed camera pair, surprisingly simple)  
Omnidirectional 
T.Svoboda, T.Pajdla, V.Hlavac. Epipolar
Geometry for Panoramic Cameras.
ECCV 1998, Springer LNCS 1406, pp. 335340, June 1998. (the first formulae
for a general epipolar geometry for central camtadioptric cameras ...
hyperbolic mirror only) T. Svoboda, T.Pajdla, V.Hlavac. Motion Estimation Using Central Panoramic Cameras. IEEE Int. Conf. on Intelligent Vehicles 1998, pp. 335340, Causual Productions October 1998. (cameras with wide field of view provide very reliable camera motion from epipolar geometry) T.Pajdla, T.Svoboda, V.Hlavac. Epipolar Geometry of Central Panoramic Cameras. In Panoramic Vision: Sensors, Theory, and Applications, pp. 85114. Springer Verlag, 2001. (Overview of many central catadioptric cameras, definition of panoramic & omnidirectional camera, epipolar geometry for hyperbolic and parabolic mirrors, point normalization for epipolar geometry estimation with omnicameras) SK.Wei, M.Urban, T.Pajdla. Stereo Matching of Catadioptric Panoramic Images. Technical report CTUCMP200008. March 2000. (epipolar alignment for central catadioptric images, search for correspondences by dynamic programming ... completefield of view leadds to better results) S. Gaechter, T. Pajdla, B.Micusik. Mirror Design for an Omnidirectional Camera with a Space Variant Imager. Workshop on Omnidirectional Vision 2001(ICAR 2001), pp. 99105, IEEE August 2001. (uniform resolution catadioptric sensor with SVAVISCA imager) T. Svoboda, T.Pajdla. Epipolar Geometry for Central Catadioptric Cameras. IJCV, 49(1):2337, Kluwer August 2002. (parabolic+hyperbolic+elliptic nirrors = all cases done) H.Bakstein, T.Pajdla. Panoramic Mosaicing with a 180 deg Field of View Lens. Workshop on Omnidirectional Vision 2002, pp. 6067, IEEE June 2002. (model of Nikon FCE8 lens, 360x360 photograpnic quality mosaic) G.Sandini, J.SantosVictor, T.Pajdla, F. Berton. OMNIVIEWS: Direct Omnidirectional Imaging Based on a Retinaline Sensor. IEEE International Conference on Sensors 2002, IEEE 2002. (SVAVISA retinalike imager combined with a suitably designed mirror  optimal resolution for low bandwidth) B.Micusik, T.Pajdla. Estimation of Omnidirectional Camera Model from Epipolar Geometry. CVPR 2003, pp. 485490, IEEE June 2003. (autocalibration of very wideangleofview (i.e. omnidirectional) lens by epipolar geometry estimation, 9 point RANSAC by Polynomial eigenvalue problem from a oinearization... for Nikon FCE8 lens) B.Micusik, T.Pajdla. Omnidirectional Camera Model and Epipolar Geometry Estimation by RANSAC with Bucketing. SCIA 2003, pp. 8390, IEEE June 2003. (RANSAC improvement bu BUCKETING in the above method) B.Micusik, T.Pajdla. Paracatadioptric Camera Autocalibration from Epipolar Geometry. ACCV 2004, Korea January 2004. (autocalibration of a paracatadioptric camera by epipolar geometry estimation can be done as a Quartic polynomial eigenvalue problem, no linearization neecessary, done for hyperbolic mirror as well) B.Micusik, D.Martinec, T.Pajdla. 3D Metric Reconstruction from Uncalibrated Omnidirectional Images. ACCV 2004, Korea January 2004. (automatic correspondece, autocalibration, and metric reconstruction from many wide baseline wideangleofview (Canon EOSD1 with Sigma 180x360 lens) images) H.Bakstein, T.Pajdla. Calibration procedure for a 360x360 mosaic camera. International archives of photogrammetry, remote sensing and spatial information sciences, XXXVI5/W8:online, February 2005. B.Micusik, T.Pajdla. Structure from Motion with Wide Circular Field of View Cameras. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 7, pp. 11351149, Jul, 2006.  
Factorization

D.Martinec, T.Pajdla. Structure from
Many Perspective Images with Occlusions.
ECCV 2002, pp. 355369, Springer LNCS, May 2002. (projective factorization with
missing data = projective depth estimation using Sturm & Triggs method +
Extension of Jacobs filling method from affine to perspective camera)
D.Martinec, T.Pajdla. Line Reconstruction from Many Perspective Images by Factorization. CVPR 2003, pp. 497502, IEEE June 2003. (projective factorization with missing data & outliers ... a little of RANSAC added to the above method) D.Martinec, T.Pajdla. Consistent MultiView Reconstruction from Epipolar Geometries with Outliers. SCIA 2003, pp. 493500, IEEE June 2003. (projective factorization can be done also for lines using Plucker coordinates) D.Martinec, T.Pajdla. 3D Reconstruction by Fitting LowRank Matrices with Missing Data. CVPR 2005, pp. 198205, IEEE June 2005. (linear formulation for computing the logarithms of projective depths, linear formulation for consistent reconstruction) T.Svoboda, D.Martinec, and T.Pajdla. A convenient multicamera selfcalibration for virtual environments. PRESENCE: Teleoperators and Virtual Environments, 14(4):407422, August 2005.  
Orientation 
T. Werner, T.Pajdla, V. Hlavac. Oriented
Projective Reconstruction. ÖAGM/IAPR,
pp. 245254, May 1998.
Best paper award. (Hartley's
cheriality rediscovered, later but independently, omnidirectional cameras
have haplrays, and thus are oriented!)  
Correspondence Localization Rendering Range 
O.Chum, T.Pajdla, P.Sturm. The Geometric Error for Homographies.
Computer Vision and Image
Understanding Volume
97, Issue 1 , January 2005, Pages 86102. J.Matas, O.Chum, M.Urban, T.Pajdla. Robust Wide Baseline Stereo from Maximally Stable Extremal Regions.Image and Vision Computing, 22(10):761767, September 2004. (The journal version of BMVC 2002 paper.) J.Matas, O.Chum, M.Urban, T.Pajdla. Robust Wide Baseline Stereo from Maximally Stable Extremal Regions. BMVC 2002, pp. 384393, BMVA Septmeber 2002. (formulation of a robust matching paradigm: Distinguished vs. Measurement regions + orderingbased similarity & RANSACbased estimation of multiview geometry) Best paper award. M.Urban, T.Pajdla, V.Hlavac. Projective Reconstruction From N Views Having One View in Common. Vision Algorithms, LNCS 1883, pp. 116131, September 1999. (projective reconstruction from many views with one view in common ... cake configuration) T.Werner, T.Pajdla, V.Hlavac. Efficient 3D Scene Visualization by Image Extrapolation. ECCV 1998, Springer LNCS 1406, pp. 382395, June 1998. (novel view synthesisby image interpolation is simpler than by image estrapolation, which is equivalent to reconstructing a the scene) T.Werner, T.Pajdla, V.Hlavac, A.Leonardis, M.Matousek. Selection of Reference Images for ImageBased Representation. Computing 68(2):163180, Springer March 2002. (reference views can be selected using reprojection error) T. Pajdla, V.Hlavac. Zero Phase Representation of Panoramic Images for Image Based Localization. CAIP 1999, Springer LNCS 1689, pp. 550557. September 1999. (image based compas from phase (Zero Phase Representation) of periodic panoramic images used for robot localization) T.Pajdla. Camera Calibration and Euclidean Reconstruction from Known Observer Translations. CVPR 1998, pp. 421426, IEEE June 1998. (linear ethod for cameraonrobot calibration using controlled translcations) P.Krsek, T.Pajdla, V.Hlavac. Differential Invariants as the Base of Triangulated Surface Registration. Computer Vision and Image Understanding 87(13):2738, Academic Press, July 2002. (differential invariants of triangulated surfaces) T.Pajdla, L.Van Gool. Matching of 3D Curves Using Semidifferential Invariants. ICCV 1995, pp. 390395, IEEE June 1995. (curve matching with ICRP = Iterative Closest Reciprocal Point Algorithm) T.Pajdla, V.Hlavac, R.Sara. Segmentation of Range Images. Acta Stereologica, 13(2):459464, June 1994. 