Data-driven image completion by image patch subspaces

Authors:
Hossein Mobahi;Shankar R. Rao;Yi Ma
Affiliations:
Coordinated Science Laboratory, University of Illinois at Urbana Champaign, Urbana, IL;Coordinated Science Laboratory, University of Illinois at Urbana Champaign, Urbana, IL;Coordinated Science Laboratory, University of Illinois at Urbana Champaign, Urbana, IL
Venue:
PCS'09 Proceedings of the 27th conference on Picture Coding Symposium
Year:
2009

Citing 7
Cited 1

Texture Synthesis by Non-Parametric Sampling

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Image Completion Using Global Optimization

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
A Visual Vocabulary for Flower Classification

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Scene completion using millions of photographs

ACM SIGGRAPH 2007 papers
From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images

SIAM Review
Simultaneous structure and texture image inpainting

IEEE Transactions on Image Processing
Sparse Representation for Color Image Restoration

IEEE Transactions on Image Processing

A high-quality low-delay remote rendering system for 3D video

Proceedings of the international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

We develop a new method for image completion on images with large missing regions. We assume that similar patches form low dimensional clusters in the image space where each cluster can be approximated by a (degenerate) Gaussian. We use sparse representation for subspace detection and then compute the most probable completion. Our results show almost no blurring or blocking effects. In addition, both the texture and structure of the missing regions look realistic to the human eye.