Inference of Segmented Color and Texture Description by Tensor Voting
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image completion with structure propagation
ACM SIGGRAPH 2005 Papers
Removing camera shake from a single photograph
ACM SIGGRAPH 2006 Papers
Technical Section: Gradient based image completion by solving the Poisson equation
Computers and Graphics
Space-Time Completion of Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
A virtual restoration stage for real-world objects
ACM SIGGRAPH Asia 2008 papers
Automatic Structure-Aware Inpainting for Complex Image Content
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Image Inpainting Considering Brightness Change and Spatial Locality of Textures and Its Evaluation
PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
International Journal of Computer Vision
Exemplar-Based Interpolation of Sparsely Sampled Images
EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
A Variational Framework for Non-local Image Inpainting
EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Removing image artifacts due to dirty camera lenses and thin occluders
ACM SIGGRAPH Asia 2009 papers
Interactive Image Inpainting Using DCT Based Exemplar Matching
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
Personal photo enhancement using example images
ACM Transactions on Graphics (TOG)
Image filling-in: a gestalt approach
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Image inpainting with a learned guidance vector field
ICICS'09 Proceedings of the 7th international conference on Information, communications and signal processing
An approach to 2D-to-3D conversion for multiview displays
ICICS'09 Proceedings of the 7th international conference on Information, communications and signal processing
A multi-scale image inpainting algorithm based on GMRF model
ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
Statistical regularities in low and high dynamic range images
Proceedings of the 7th Symposium on Applied Perception in Graphics and Visualization
Image inpainting by patch propagation using patch sparsity
IEEE Transactions on Image Processing
Estimating vignetting function from a single image for image authentication
Proceedings of the 12th ACM workshop on Multimedia and security
Fast query for exemplar-based image completion
IEEE Transactions on Image Processing
Automatic image interpolation using homography
EURASIP Journal on Advances in Signal Processing
Generating shaded image with lighting using image fusion space
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part III
A Variational Framework for Exemplar-Based Image Inpainting
International Journal of Computer Vision
Gradient based image completion by solving poisson equation
PCM'05 Proceedings of the 6th Pacific-Rim conference on Advances in Multimedia Information Processing - Volume Part I
Statistics of patch offsets for image completion
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Repairing sparse low-rank texture
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
| Hi-index | 0.00 |
Inpainting is the problem of filling-in holes in images.Considerable progress has been made by techniques that use theimmediate boundary of the hole and some prior information on imagesto solve this problem. These algorithms successfully solve thelocal inpainting problem but they must, by definition, give thesame completion to any two holes that have the same boundary, evenwhen the rest of the image is vastly different. In this paper weaddress a different, more global inpainting problem. How can we usethe rest of the image in order to learn how to inpaint? We approachthis problem from the context of statistical learning. Given atraining image we build an exponential family distribution overimages that is based on the histograms of local features. We thenuse this image specific distribution to in paint the hole byfinding the most probable image given the boundary and thedistribution. The optimization is done using loopy beliefpropagation. We show that our method can successfully completeholes while taking into account the specific image statistics. Inparticular it can give vastly different completions even when thelocal neighborhoods are identical.