Label transfer exploiting three-dimensional structure for semantic segmentation

Authors:
Valeria Garro;Andrea Fusiello;Silvio Savarese
Affiliations:
DI, University of Verona, Verona (Italy);DIEGM, University of Udine, Udine (Italy);EECS, University of Michigan, Ann Arbor, MI
Venue:
Proceedings of the 6th International Conference on Computer Vision / Computer Graphics Collaboration Techniques and Applications
Year:
2013

Citing 12
Cited 0

Removing Shadows from Images

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Video Google: A Text Retrieval Approach to Object Matching in Videos

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Photo tourism: exploring photo collections in 3D

ACM SIGGRAPH 2006 Papers
Convergent Tree-Reweighted Message Passing for Energy Minimization

IEEE Transactions on Pattern Analysis and Machine Intelligence
Modeling the World from Internet Photo Collections

International Journal of Computer Vision
SIFT Flow: Dense Correspondence across Different Scenes

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Segmentation and Recognition Using Structure from Motion Point Clouds

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Building Rome on a cloudless day

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Superparsing: scalable nonparametric image parsing with superpixels

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Supervised label transfer for semantic segmentation of street scenes

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

IEEE Transactions on Pattern Analysis and Machine Intelligence
PATCHMATCHGRAPH: building a graph of dense patch correspondences for label transfer

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with the problem of computing a semantic segmentation of an image via label transfer from an already labeled image set. In particular it proposes a method that takes advantage of sparse 3D structure to infer the category of superpixel in the novel image. The label assignment is computed by a Markov random field that has the superpixels of the image as nodes. The data term combines labeling proposals from the appearance of the superpixel and from the 3D structure, while the pairwise term incorporates spatial context, both in the image and in 3D space. Exploratory results indicate that 3D structure, albeit sparse, improves the process of label transfer.