A volumetric method for building complex models from range images
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
Computing Geodesics and Minimal Surfaces via Graph Cuts
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Silhouette and stereo fusion for 3D object modeling
Computer Vision and Image Understanding - Model-based and image-based 3D scene representation for interactive visalization
Multi-View Stereo via Volumetric Graph-Cuts
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Symmetric Stereo Matching for Occlusion Handling
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Efficient Dense Stereo with Occlusions for New View-Synthesis by Four-State Dynamic Programming
International Journal of Computer Vision
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Convergent Tree-Reweighted Message Passing for Energy Minimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiview Stereo via Volumetric Graph-Cuts and Occlusion Robust Photo-Consistency
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust and efficient photo-consistency estimation for volumetric 3d reconstruction
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
An iterative surface evolution algorithm for multiview stereo
Journal on Image and Video Processing - Special issue on fast and robust methods for multiple-view vision
Joint Multi-Layer Segmentation and Reconstruction for Free-Viewpoint Video Applications
International Journal of Computer Vision
Editor's Choice Article: Video-based, real-time multi-view stereo
Image and Vision Computing
Embedded Voxel Colouring with Adaptive Threshold Selection Using Globally Minimal Surfaces
International Journal of Computer Vision
Scale robust multi view stereo
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Hallucination-Free multi-view stereo
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
Multimedia Tools and Applications
A bayesian approach to uncertainty-based depth map super resolution
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
An efficient image matching method for multi-view stereo
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
Coupled structure-from-motion and 3D symmetry detection for urban facades
ACM Transactions on Graphics (TOG)
Technical Section: High-resolution depth for binocular image-based modeling
Computers and Graphics
Real-time generation of multi-view video plus depth content using mixed narrow and wide baseline
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
We propose an algorithm to improve the quality of depth-maps used for Multi-View Stereo (MVS). Many existing MVS techniques make use of a two stage approach which estimates depth-maps from neighbouring images and then merges them to extract a final surface. Often the depth-maps used for the merging stage will contain outliers due to errors in the matching process. Traditional systems exploit redundancy in the image sequence (the surface is seen in many views), in order to make the final surface estimate robust to these outliers. In the case of sparse data sets there is often insufficient redundancy and thus performance degrades as the number of images decreases. In order to improve performance in these circumstances it is necessary to remove the outliers from the depth-maps. We identify the two main sources of outliers in a top performing algorithm: (1) spurious matches due to repeated texture and (2) matching failure due to occlusion, distortion and lack of texture. We propose two contributions to tackle these failure modes. Firstly, we store multiple depth hypotheses and use a spatial consistency constraint to extract the true depth. Secondly, we allow the algorithm to return an unknownstate when the a true depth estimate cannot be found. By combining these in a discrete label MRF optimisation we are able to obtain high accuracy depth-maps with low numbers of outliers. We evaluate our algorithm in a multi-view stereo framework and find it to confer state-of-the-art performance with the leading techniques, in particular on the standard evaluation sparse data sets.