In this study, the authors propose an approach towards dense depth reconstruction, combining robust feature-based structure from motion with the spatial coherence of dense reconstruction algorithms. To achieve this, a variational framework was set up, minimising the epipolar reprojection error and the image brightness constraint, while preserving discontinuities in the depth field by introducing an anisotropic diffusion term. As initial guess for the iterative solver, a region growing algorithm is proposed which mixes sparse and dense data.
Inspec keywords: image sequences; image reconstruction; partial differential equations; iterative methods
Other keywords:
Subjects: Differential equations (numerical analysis); Differential equations (numerical analysis); Interpolation and function approximation (numerical analysis); Interpolation and function approximation (numerical analysis); Computer vision and image processing techniques; Optical, image and video signal processing
References
-
-
1)
- Faugeras, O.D., Keriven, R.: `Complete dense stereovision using level set methods', ECCV 98: Proc. Fifth European Conf. on Computer Vision, 1998, 1, p. 379–393.
-
2)
- L. Alvarez , C. Cuenca , A. Salgado , J. Sanchez . A variational approach to 3d cylindrical geometry reconstruction from multiple views. Electron. Lett. Comput. Vis. Image Anal. , 2 , 54 - 66
-
3)
- Strecha, C., Van Gool, L.: `Pde-based multi-view depth estimation', First Int. Symp. on 3D Data Processing Visualization and Transmission (3DPVT02), 2002, p. 22.
-
4)
- H. Zimmer , A. Bruhn , L. Valgaerts . PDE-based anisotropic disparity-driven stereo vision. Vis. Model. Vis. , 263 - 272
-
5)
- Jancosek, M., Pajdla, T.: 2009 Segmentation based multi-view stereo. CVWW, 2009.
-
6)
- Z. Zhang . Iterative point matching for registration of free-form curves and surfaces. Int. J. Comput. Vis. , 2 , 119 - 152
-
7)
- A. Mitiche , S. Hadjres . Mdl estimation of a dense map of relative depth and 3d motion from a temporal sequence of images. Pattern Anal. Appl. , 1 , 78 - 87
-
8)
- R. Hartley . (2003) Multiple view geometry in computer vision.
-
9)
- C. Strecha , W. von Hansen , L.V. Gool , P. Fua , U. Thoennessen . On benchmarking camera calibration and multi-view stereo for high resolution imagery. Comput. Vis. Pattern Recognit. , 1 - 8
-
10)
- H. Nagel , W. Enkelmann . An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. Pattern Anal. Mach. Intell. , 5 , 565 - 593
-
11)
- H.C. Longuet-Higgins . A computer algorithm for reconstructing a scene from two projections. Nature , 5828 , 133 - 135
-
12)
- Yang, L.: `Structure and motion analysis: variational methods and related PDE models', 2004, PhD, Vrije Universiteit Brussel.
-
13)
- Y. Furukawa , J. Ponce . Accurate, dense, and robust multi-view stereopsis. Comput. Vis. Pattern Recognit. , 1 - 8
-
14)
- B.K.P. Horn . (1986) Robot vision.
-
15)
- Slesareva, N., Bhler, T., Hagenburg, K.U.: `Robust variational reconstruction from multiple views', SCIA, 2007, 4522, p. 173–182.
-
16)
- S. Ullman . (1979) The interpretation of visual motion.
-
17)
- S. Chen , Y. Wang , C. Cattani . Key issues in modeling of complex 3d structures from video sequences. Math. Probl. Eng.
-
18)
- Zaharescu, A., Boyer, E., Horaud, R.: `Transformesh a topology-adaptive mesh-based approach to surface evolution', ACCV, 2007.
-
19)
- Strecha, C., Fransen, R., Van Gool, L.: `Wide-baseline stereo from multiple views: a probabilistic account', IEEE Conf. on Computer Vision and Pattern Recognition, 2004, 2, p. 552–559.
-
20)
- T. Coleman , Y. Li . A reflective Newton method for minimizing a quadratic function subject to bounds on some of the variables. SIAM J. Optim. , 4 , 1040 - 1058
-
21)
- H. Sekkati , A. Mitiche . A variational method for the recovery of dense 3d structure from motion. Robot. Auton. Syst. , 7 , 597 - 607
-
22)
- Tylecek, R., Sara, R.: 2009 Depth map fusion with camera position refinement. CVWW, 2009.
-
23)
- Alvarez, L., Deriche, R., Weickert, J., Sanchez, J.: `Dense disparity map estimation respecting image discontinuities: a PDE and scale-space based approach', IAPR Int. Workshop on Machine Vision Applications, 2000.
-
24)
- H. Vu , R. Keriven , P. Labatut , J.P. Pons . Towards high-resolution large-scale multi-view stereo. Comput. Vis. Pattern Recognit. , 1430 - 1437
-
25)
- Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: `A comparison and evaluation of multi-view stereo reconstruction algorithms', CVPR ’06: Proc. 2006 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2006, p. 519–528.
-
26)
- P.H.S. Torr , A. Zisserman . Mlesac: a new robust estimator with application to estimating image geometry. Comput. Vis. Image Underst. , 1 , 138 - 156
-
27)
- Yezzi, A.J., Soatto, S.: `Structure from motion for scenes without features', Proc. 2003 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, June 2003, 1, p. 525–532.
-
28)
- C. Strecha , R. Fransens , L. Van Gool . Combined depth and outlier estimation in multi-view stereo. Comput. Vis. Pattern Recognit. , 2394 - 2401
-
29)
- V. Kolmogorov , R. Zabih . Multi-camera scene reconstruction via graph cuts. European Conf. on Computer Vision , 82 - 96
-
30)
- Hartley, R.I., Sturm, P.: `Triangulation', American Image Understanding Workshop, 1994, p. 957–966.
-
1)
Related content