A Convex Relaxation Approach to Space Time Multi-view 3D Reconstruction

Martin R. Oswald, Daniel Cremers
Department of Computer Science, TU Munchen
2nd International Workshop on Dynamic Shape Capture and Analysis (4DMOD), The IEEE International Conference on Computer Vision (ICCV) Workshops, 2013


   author={Martin R. Oswald and Daniel Cremers},

   title={A Convex Relaxation Approach to Space Time Multi-view 3D Reconstruction},

   journal={The IEEE International Conference on Computer Vision (ICCV) Workshops},




Download Download (PDF)   View View   Source Source   



We propose a convex relaxation approach to space-time 3D reconstruction from multiple videos. Generalizing the works [16], [8] to the 4D setting, we cast the problem of reconstruction over time as a binary labeling problem in a 4D space. We propose a variational formulation which combines a photoconsistency based data term with a spatio-temporal total variation regularization. In particular, we propose a novel data term that is both faster to compute and better suited for wide-baseline camera setups when photoconsistency measures are unreliable or missing. The proposed functional can be globally minimized using convex relaxation techniques. Numerous experiments on a variety of publically available data sets demonstrate that we can compute detailed and temporally consistent reconstructions. In particular, the temporal regularization allows to reduce jittering of voxels over time.
No votes yet.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: