a fast spatial patch blending algorithm for artefact
play

A Fast Spatial Patch Blending Algorithm for Artefact Reduction in - PowerPoint PPT Presentation

Sep 11, 2022 •121 likes •542 views

A Fast Spatial Patch Blending Algorithm for Artefact Reduction in Pattern-based Image Inpainting Maxime Daisy, David Tschumperl e, Olivier L ezoray GREYC - UMR 6072 CNRS, ENSICAEN, University of Caen Image team SIGGRAPH Asia 21

  1. A Fast Spatial Patch Blending Algorithm for Artefact Reduction in Pattern-based Image Inpainting Maxime Daisy, David Tschumperl´ e, Olivier L´ ezoray GREYC - UMR 6072 CNRS, ENSICAEN, University of Caen Image team SIGGRAPH Asia 21 November 2013

  2. Outlines 1 Inpainting : Context and State of the Art 2 Patch Blending for Inpainting 3 Results and Comparisons M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 2 / 41

  3. Outlines 1 Inpainting : Context and State of the Art 2 Patch Blending for Inpainting 3 Results and Comparisons M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 3 / 41

  4. Image Inpainting : Overview Original M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 4 / 41

  5. Image Inpainting : Overview Masked image M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 5 / 41

  6. Image Inpainting : Overview Inpainted image M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 6 / 41

  7. Image Inpainting : a little history • Masnou and Morel : Level lines based disocclusion, ICIP 1998 • Efros and Leung : Texture synthesis by non-parametric sampling, ICCV 1999 • Bertalm´ ıo et al. : Image Inpainting, SIGGRAPH 2000 • Criminisi et al. : Object Removal by Exemplar-based Inpainting, CVPR 2003 • Wexler et al. : Space-time video completion, CVPR 2004 • Sun et al. : Image Inpainting by Patch Propagation Using Patch Sparsity IEEE 2010 • Darabi et al. : Image Melding : Combining Inconsistent Images using Patch-based Synthesis, SIGGRAPH 2012 • . . . M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 7 / 41

  8. Criminisi et al. : overview M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 8 / 41

  9. Good texture reconstruction M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 9 / 41

  10. Good texture reconstruction M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 10 / 41

  11. Local geometry inconsistencies M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 11 / 41

  12. Since Criminisi et al. 2003 inpainting algorithm Content Aware Filling 2010 • Wexler et al. 2007 : Space-time completion of videos • Barnes et al. 2009 : PatchMatch ⇒ blurry textures Le Meur et al. 2011 • local geometry aware : structure tensors analysis • K-nearest neighbours averaging ⇒ blurry textures, geometry inconsitencies M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 12 / 41

  13. Since Criminisi et al. 2003 inpainting algorithm (a) Content-aware filling (b) Le Meur et al. 2011 M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 13 / 41

  14. The question How to keep both good textures and geometry consistency ? M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 14 / 41

  15. Outlines 1 Inpainting : Context and State of the Art 2 Patch Blending for Inpainting 3 Results and Comparisons M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 15 / 41

  16. Spatial patch blending - Extreme case Masked image. M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 16 / 41

  17. Spatial patch blending - Extreme case Inpainted image : Criminis et al. 2003. M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 17 / 41

  18. Spatial patch blending - Extreme case Diffusion PDE inpainting result. M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 18 / 41

  19. Spatial patch blending - Extreme case Content-aware filling algorithm. M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 19 / 41

  20. Spatial patch blending - Extreme case Effect of spatial patch blending. M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 20 / 41

  21. σ ( p ) : an adaptative blending amplitude (c) Break field R ( p ) (d) Blending amplitude field σ ( p ) M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 21 / 41

  22. Spatial Patch Blending : explanation M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 22 / 41

  23. Mathematical expression • Usage of reconstruction points and patch locations, saved during inpainting process w ( q , p ) ψ i q ( p − q ) ∑ ψ q ∈ Ψ p J i ( p ) = ε + ∑ w ( q , p ) ψ q ∈ Ψ p • Ψ p : set of patches used for the reconstruction around p q ( p − q ) : pixel value at (( N / 2 , N / 2 ) T +( p − q )) in ψ i • ψ i q • σ ( p ) : blending amplitude at p • w ( q , p ) gaussian weight of variance σ ( p ) 2 M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 23 / 41

  24. Fast algorithm - Blend scales M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 24 / 41

  25. Outlines 1 Inpainting : Context and State of the Art 2 Patch Blending for Inpainting 3 Results and Comparisons M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 25 / 41

  26. Time Comparison M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 26 / 41

  27. Result - Nature Original Image M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 27 / 41

  28. Result - Nature Content-aware Filling M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 28 / 41

  29. Result - Nature Criminisi + our spatial patch blending M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 29 / 41

  30. Result - Fake Owl Original Image M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 30 / 41

  31. Result - Fake Owl Criminisi et al. 2004 M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 31 / 41

  32. Result - Fake Owl Content-aware Filling M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 32 / 41

  33. Result - Fake Owl Criminisi + our spatial patch blending M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 33 / 41

  34. Result - Savanna Original Image M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 34 / 41

  35. Result - Savanna Criminisi et al. 2005 M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 35 / 41

  36. Result - Savanna Content-aware Filling M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 36 / 41

  37. Result - Savanna Criminisi + our spatial patch blending M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 37 / 41

  38. GIMP Software Integration : G’MIC plugin M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 38 / 41

  39. GIMP Software Integration : G’MIC plugin M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 39 / 41

  40. GIMP Software Integration : G’MIC plugin M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 40 / 41

  41. GIMP Software Integration : G’MIC plugin M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 41 / 41

  42. GIMP Software Integration : G’MIC plugin M. Daisy (GREYC) SIGGRAPH Asia 2013 21 November 2013 42 / 41

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

http://www.writingwrocks.com/eportfolio/view/artefact.php?artefact=19132&view=4623

http://www.writingwrocks.com/eportfolio/view/artefact.php?artefact=19132&view=4623

http://www.writingwrocks.com/eportfolio/view/artefact.php?artefact=19132&view=4623 http://www.writingwrocks.com/eportfolio/view/artefact.php?artefact=16954&view=3069 What are the experiences of faculty who Gender Degree Years Division

911 views • 9 slides
Supplement 189: Parametric Blending Presentation State Storage 1 Overview Objective

Supplement 189: Parametric Blending Presentation State Storage 1 Overview Objective

Supplement 189: Parametric Blending Presentation State Storage 1 Overview Objective Input data Blending operation Example 2 Blending Presentation State introduction Objective Allowing to show spatial relationship of

477 views • 16 slides
Is This Algorithm Fast? Topic Number 8 op c u be 8 Problem: given a problem, how fast does

Is This Algorithm Fast? Topic Number 8 op c u be 8 Problem: given a problem, how fast does

Is This Algorithm Fast? Topic Number 8 op c u be 8 Problem: given a problem, how fast does this Algorithm Analysis code solve that problem? Could try to measure the time it takes, but " bit twiddling: 1. (pejorative) An exercise

396 views • 15 slides
Will My Patch Make It? And How Fast? Yujuan Jiang, Bram Adams (MCIS, Polytechnique Montral)

Will My Patch Make It? And How Fast? Yujuan Jiang, Bram Adams (MCIS, Polytechnique Montral)

Will My Patch Make It? And How Fast? Yujuan Jiang, Bram Adams (MCIS, Polytechnique Montral) Daniel M. German (University of Victoria ) 1 Monday, 3 June, 13 I do hold out hope that Google does come around and works to fix their codebase to

1.05k views • 57 slides
An Open Platform for Digitizing Real World through Sentient Artefact Model Fahim Kawsar Waseda

An Open Platform for Digitizing Real World through Sentient Artefact Model Fahim Kawsar Waseda

An Open Platform for Digitizing Real World through Sentient Artefact Model Fahim Kawsar Waseda University, Japan 1 Talk Outline Motivation Scenario Sentient Artefact Design Principle Sentient Artefact Development

323 views • 31 slides
Preparation for Blending Mr Don McWhirter MacWool Ltd Blending of Greasy Wool Extremely

Preparation for Blending Mr Don McWhirter MacWool Ltd Blending of Greasy Wool Extremely

Preparation for Blending Mr Don McWhirter MacWool Ltd Blending of Greasy Wool Extremely important in early stage processing Primary purpose is to produce an even and uniform top Pre-delivery/Preparation for Blending Purchase

1.28k views • 50 slides
Blending Blending Elements of two input spaces are projected into a third space, the

Blending Blending Elements of two input spaces are projected into a third space, the

Blending Blending Elements of two input spaces are projected into a third space, the blend, which contains elements of both, but is distinct from either one Non-linguistic blending Faces seen as combinations of parents

608 views • 24 slides
An Artefact Repository to Support Distributed Software Engineering October 29, 2004 1

An Artefact Repository to Support Distributed Software Engineering October 29, 2004 1

An Artefact Repository to Support Distributed Software Engineering October 29, 2004 1 Introduction The Open Source Component Artefact Repository (OSCAR) is an internet based system designed and built for use within the GENESIS process aware

688 views • 7 slides
Neural Networks applied to Blending Challenges Sowmya Kamath, Patricia Burchat Blending

Neural Networks applied to Blending Challenges Sowmya Kamath, Patricia Burchat Blending

Neural Networks applied to Blending Challenges Sowmya Kamath, Patricia Burchat Blending Workshop, 15th August, 2018 Blending & Neural Networks Object detection and instance segmentation is an active area of research in computer vision

528 views • 19 slides
Blending Blending Combining familiar spaces (domains of understanding, mental

Blending Blending Combining familiar spaces (domains of understanding, mental

Blending Blending Combining familiar spaces (domains of understanding, mental simulations, motor routines) to produce novel space with emergent structure General cognitive process Accidental or Creative Linguistic or

272 views • 24 slides
Hoare logic and Model checking If we can express the artefact as a temporal model too, and if the

Hoare logic and Model checking If we can express the artefact as a temporal model too, and if the

Hoare logic and Model checking If we can express the artefact as a temporal model too, and if the crucial aspects of the artefact. ...still, another crucial aspect of modelling is to not discard the M Abstraction of traffjc lights by some

538 views • 4 slides
Blending in LSST Data Products Jim Bosch, DM DRP Scientist / Princeton Blending Families Two

Blending in LSST Data Products Jim Bosch, DM DRP Scientist / Princeton Blending Families Two

Blending in LSST Data Products Jim Bosch, DM DRP Scientist / Princeton Blending Families Two Footprints: 2 above-threshold regions with peaks. 4 One isolated object ( 1 ). 3 One Parent ( 2 ): 5 blends measured with no deblending. Three

216 views • 20 slides
Modeling Algorithm for Test Cost Reduction of Analog/RF Circuits Hugo Gonalves 1,2 , Xin Li 1 ,

Modeling Algorithm for Test Cost Reduction of Analog/RF Circuits Hugo Gonalves 1,2 , Xin Li 1 ,

A Fast Wafer-Level Spatial Variation Modeling Algorithm for Test Cost Reduction of Analog/RF Circuits Hugo Gonalves 1,2 , Xin Li 1 , Miguel Correia 2 and Vitor Tavares 2 1 ECE Department, Carnegie Mellon University, USA 2 Faculdade de

480 views • 27 slides
Blending Wool for a uniform top which meets specification Martin Prins CSIRO FIBRE BLENDING

Blending Wool for a uniform top which meets specification Martin Prins CSIRO FIBRE BLENDING

FIBRE BLENDING Martin Prins Blending Wool for a uniform top which meets specification Martin Prins CSIRO FIBRE BLENDING Consists of selecting the right amounts of suitable wools to fulfil an order & then mixing them to give a uniform

726 views • 26 slides
A PROPORTIONATE AFFINE PROJECTION ALGORITHM USING FAST RECURSIVE FILTERING AND DICHOTOMOUS

A PROPORTIONATE AFFINE PROJECTION ALGORITHM USING FAST RECURSIVE FILTERING AND DICHOTOMOUS

A PROPORTIONATE AFFINE PROJECTION ALGORITHM USING FAST RECURSIVE FILTERING AND DICHOTOMOUS COORDINATE DESCENT ITERATIONS Felix Albu Valahia University of Targoviste Outline Motivation and objectives Development of the algorithm Simulation

668 views • 19 slides
An Analysis of Patch Plausibility and Correctness of

An Analysis of Patch Plausibility and Correctness of

An Analysis of Patch Plausibility and Correctness of Generate-And- Validate Patch Genera8on System Zichao Qi , Fan Long, Sara Achour, and Mar8n Rinard MIT

323 views • 29 slides
Curvature line parametrized surfaces and orthogonal coordinate systems Discretization with

Curvature line parametrized surfaces and orthogonal coordinate systems Discretization with

Curvature line parametrized surfaces and orthogonal coordinate systems Discretization with Dupin cyclides Emanuel Huhnen-Venedey, TU Berlin Diploma thesis supervised by A.I. Bobenko Structure of the talk Curvature line parametrized

224 views • 19 slides
Curves and paths in space Example : Define ( t ) := (cos t, sin t ) , t [0 , 1] . This

Curves and paths in space Example : Define ( t ) := (cos t, sin t ) , t [0 , 1] . This

Curves and paths in space Example : Define ( t ) := (cos t, sin t ) , t [0 , 1] . This defines a function or mapping : [0 , 1] R 2 . This function is called a path in the plane R 2 . If we plot ( t ) versus 0 t 1 then we

407 views • 18 slides
VECTOR-VALUED FUNCTIONS MATH 200 MAIN QUESTIONS FOR TODAY Whats a vector valued function?

VECTOR-VALUED FUNCTIONS MATH 200 MAIN QUESTIONS FOR TODAY Whats a vector valued function?

MATH 200 WEEK 3 - WEDNESDAY VECTOR-VALUED FUNCTIONS MATH 200 MAIN QUESTIONS FOR TODAY Whats a vector valued function? How do we find the domain of a vector valued function? How do we compute the derivative of a vector-valued

523 views • 13 slides
Ultraquadrics and its application to the reparametrization of rational complex surfaces C ARLOS V

Ultraquadrics and its application to the reparametrization of rational complex surfaces C ARLOS V

RICAM Computer algebra and polynomials. November 25-29, 2013. Ultraquadrics and its application to the reparametrization of rational complex surfaces C ARLOS V ILLARINO A CKNOWLEDGMENT : T HIS WORK HAS BEEN DONE UNDER THE RESEARCH PROJECT

351 views • 33 slides
Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio

Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio

Setting - 2 Task Setting - 1 Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations Method Ju-chieh Chou , Cheng-chieh Yeh, Hung-yi Lee, Lin-shan Lee Best student paper award nominated

532 views • 25 slides
Modeling images The order of presentations will be chosen randomly Subhransu Maji Remaning

Modeling images The order of presentations will be chosen randomly Subhransu Maji Remaning

Administrivia This is the last lecture! Next two will be project presentations by you Upload your presentations on Moodle by 11 AM, Thursday, Dec. 8 6 min presentation + 2 mins of questions Modeling images The order of presentations

100 views • 9 slides
Michele Selvaggi , for the Delphes Team Universit catholique de Louvain (UCL) Center for

Michele Selvaggi , for the Delphes Team Universit catholique de Louvain (UCL) Center for

Michele Selvaggi , for the Delphes Team Universit catholique de Louvain (UCL) Center for Particle Physics and Phenomenology (CP3) JHEP 02 (2014) 057 SLAC 100 TeV workshop 23 April 2014 Outline The Delphes Project Event

673 views • 30 slides
Geodesic computation on a graph Graph: ( V, E ), V = { 1 , . . . , n } , E V 2 (symmetric). j

Geodesic computation on a graph Graph: ( V, E ), V = { 1 , . . . , n } , E V 2 (symmetric). j

Geodesics and Fast Marching Methods Gabriel Peyr Laurent Cohen Jean-Marie Mirebeau C O L E N O R M A L E S U P R I E U R E Geodesic computation on a graph Graph: ( V, E ), V = { 1 , . . . , n } , E V 2 (symmetric). j y w i,j

325 views • 20 slides

More recommend