Download presentation
Presentation is loading. Please wait.
Published byDominick McCormick Modified over 8 years ago
1
Image Inpainting Marcelo Bertalmío, Minnesota
Guillermo Sapiro, Minnesota Vicent Caselles, Barcelona Coloma Ballester, Barcelona SIGGRAPH ‘00
2
Overview What is image inpainting Related work Digital inpainting
Examples Concluding remarks
3
What is inpainting? Modifying an image in a non-detectable form
Detail of "Cornelia, Mother of the Gracchi" by J. Suvee (Louvre). Taken from Emile-Male “The Restorer’s Handbook of easel painting”.
4
Photo restoration Restoration courtesy of D. Henry, Precious Photos Inc.
5
Object removal From D. King, “The Commissar vanishes”.
6
Related work: Films n-1 n n+1 e.g. Kokaram et al.
Doesn’t work for stills or static objects n-1 n n+1
7
Related work: Texture synthesis
Hirani, Efros, Heeger, DeBonet, Simoncelli, etc. Not practical for rich regions Not designed for structured regions “Copy” information instead of “learn and interpolate”
8
Related work: Disocclusion
Masnou-Morel, Nitzberg-Mumford, etc. Limitations: Topology, angles See also Chan-Shen ‘00
9
Our Contribution User only selects region to inpaint
Rich background and topology not an issue Less than 5 minutes on a PC + =
10
How conservators inpaint
Minneapolis Institute of Art
11
Automatic digital inpainting
Propagate information Evolutionary form
12
Digital inpainting (cont’d)
L = smoothness estimator (Laplacian) N = isophote direction (time variant)
13
The equation Plus numerical schemes (Osher) Boundary conditions
Gray values (in a band) Directions (in a band)
14
Example
15
Example: Text removal
16
Example: Photo restoration
17
Example: Special effects
18
Example: Scratch removal
19
Example: The evolution
20
Example: Structure but not texture is reproduced.
21
Extension: A variational formulation
Solved via E-L: Coupled 2nd order PDE’s Full theory given Similar practical results than 3rd order equation See also Chan-Shen ‘00
22
Concluding remarks Technique imitates professionals Key concepts
Information propagation Both gray values and directions are needed Use a band surrounding the region Sharp results Low complexity Texture is not reproduced
23
Concluding remarks (cont.)
Connected to thin film and fluid dynamics (A. Betozzi) Opens then door to high order PDE’s Extended to a variational formulation
24
Acknowledgments Institute Henri Poincare in Paris, France.
Tom Robbins, Elizabeth Buschor, Santiago Betelú, Stan Osher, Eero Simoncelli, Andrea Bertozzi. Supported by ONR-Math, ONR Young Investigator Award, Presidential Early Career Awards for Scientists and Engineers, NSF CAREER Award, NSF-LIS, and IIE-Uruguay.
25
The end Thank you
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.