Fast query for exemplar-based image completion

Authors:
Tsz-Ho Kwok;Hoi Sheung;Charlie C. L. Wang
Affiliations:
Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong;Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong;Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong
Venue:
IEEE Transactions on Image Processing
Year:
2010

Citing 20
Cited 4

Fast multiresolution image querying

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Wavelets for computer graphics: theory and applications

Wavelets for computer graphics: theory and applications
Image inpainting

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Fast texture synthesis using tree-structured vector quantization

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Fragment-based image completion

ACM SIGGRAPH 2003 Papers
The space of human body shapes: reconstruction and parameterization from range scans

ACM SIGGRAPH 2003 Papers
Learning How to Inpaint from Global Image Statistics

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Parallel controllable texture synthesis

ACM SIGGRAPH 2005 Papers
Image completion with structure propagation

ACM SIGGRAPH 2005 Papers
Image Completion Using Global Optimization

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Space-Time Completion of Video

IEEE Transactions on Pattern Analysis and Machine Intelligence
Scene completion using millions of photographs

ACM SIGGRAPH 2007 papers
Image completion based on views of large displacement

The Visual Computer: International Journal of Computer Graphics
Intrinsic colorization

ACM SIGGRAPH Asia 2008 papers
PatchMatch: a randomized correspondence algorithm for structural image editing

ACM SIGGRAPH 2009 papers
Rapid image completion system using multiresolution patch-based directional and nondirectional approaches

IEEE Transactions on Image Processing
Image Repairing: robust image synthesis by adaptive ND tensor voting

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Hidden digital watermarks in images

IEEE Transactions on Image Processing
Region filling and object removal by exemplar-based image inpainting

IEEE Transactions on Image Processing
Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color Images

IEEE Transactions on Image Processing

ParXII: optimized, data-parallel exemplar-based image inpainting

ACM SIGGRAPH 2011 Posters
The use of high-pass filters and the inpainting method to clouds removal and their impact on satellite images classification

ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing - Volume Part II
Technical Section: Combined frequency and spatial domain-based patch propagation for image completion

Computers and Graphics
Iterative gradient-driven patch-based inpainting

PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part II

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, we present a fast algorithm for filling unknown regions in an image using the strategy of exemplar-matching. Unlike the original exemplar-based method using exhaustive search, we decompose exemplars into the frequency coefficients and select fewer coefficients which are the most significant to evaluate the matching score. We have also developed a local gradient-based algorithm to fill the unknown pixels in a query image block. These two techniques bring the ability of input with varied dimensions to the fast query of similar image exemplars. The fast query is based upon a search-array data structure, and can be conducted very efficiently. Moreover, the evaluation of search-arrays runs in parallel maps well on the modern graphics hardware with graphics processing units (GPU). The functionality of the approach has been demonstrated by experimental results on real photographs.