super resolution via image recapture and bayesian effect
play

Super-Resolution via Image Recapture and Bayesian Effect Modeling - PowerPoint PPT Presentation

Super-Resolution via Image Recapture and Bayesian Effect Modeling Neil Toronto Oral Thesis Defense Department of Computer Science Brigham Young University December 2008 Single-Frame Super-Resolution (i.e. Good Image Magnification)


  1. Super-Resolution via Image Recapture and Bayesian Effect Modeling Neil Toronto Oral Thesis Defense Department of Computer Science Brigham Young University December 2008

  2. Single-Frame Super-Resolution (i.e. Good Image Magnification)  Printing photos from a camera or the Internet  Compositing images  Signal conversion (e.g. DVD to HDTV)  Crime drama television, blackmail  Generally an underconstrained, ill-posed problem  General solution: make it well-posed and make assumptions, then infer the extra information Super-Resolution via Image Recapture and Bayesian Effect Modeling 2

  3. Size vs. Apparent Resolution Bilinear Nearest neighbor (NN) Input Sinc ??? Super-Resolution via Image Recapture and Bayesian Effect Modeling 3

  4. Nonadaptive Methods  Assume the pixels are a function or signal sample  Families: function-fitting, frequency-domain  Implementation of both: sum up scaled copies of the same fuzzy shape (kernel)  Artifacts: Blocky: Blurry: Bilinear Bicubic Sinc  Only two possible solutions: get more data, make stronger assumptions Super-Resolution via Image Recapture and Bayesian Effect Modeling 4

  5. Adaptive Methods  Make strong assumptions  Families: edge-preserving, training- based, optimization  Examples:  Resolution synthesis (RS), local correlation (LCSR): learn optimal kernels Local correlation (LCSR) from examples, apply locally according to class  Image analogies, Freeman’s MRFs: Construct Frankenimages from Flickr  Level-set reconstruction: optimize upscaled result with respect to rewarding accuracy and penalizing jaggies Resolution synthesis (RS) Super-Resolution via Image Recapture and Bayesian Effect Modeling 5

  6. Quantitative Comparison Popularly mean-squared error  on downscaled and Original images reconstructed images, results compared against nonadaptive whipping-boys Decimation Ouwerkerk 2006: First ever  qualitative and quantitative survey of super-resolution Super- resolution Tested nine  Correctness methods on ? measures ? seven test ? images using three measures of correctness The winners: resolution synthesis (RS)  and local correlation (LCSR) Reconstructed images Super-Resolution via Image Recapture and Bayesian Effect Modeling 6

  7. Motivation 2x 4x LCSR RS Bayesian edge inference (BEI) Objective: avoid these artifacts, be competitive on Ouwerkerk’s measures Super-Resolution via Image Recapture and Bayesian Effect Modeling 7

  8. Optimization Reconstruction Framework  Reconstruction the mostly Bayesian way  Assumptions: an image I ’ existed that was degraded to produce I Image prior  Task: given I , reconstruct I ’  Reconstruct using Bayes’ Law: Degradation P  I' ∣ I = P  I ∣ I'  P  I'  P  I   Result is almost always argmax P ( I ’| I) (a “MAP estimate”) Super-Resolution via Image Recapture and Bayesian Effect Modeling 8

  9. Modeling Mismatch 1: Printing a Full-Resolution Photo There’s no higher-resolution original image to reconstruct Super-Resolution via Image Recapture and Bayesian Effect Modeling 9

  10. Modeling Mismatch 2: CCD Demosaicing There’s no pristine, unfiltered original image to reconstruct Super-Resolution via Image Recapture and Bayesian Effect Modeling 10

  11. Recapture Reconstruction Framework Assumptions: a scene S  was captured with C to create image I Task: given I (and possibly  C ), reconstruct S , and recapture it as I ’ using a fictional C ’ P  I' ∣ I =⋯ Super-Resolution via Image Recapture and Bayesian Effect Modeling 11

  12. Using the Recapture Framework 1 Define scene model S 1 1 1 2 Define capture process I | S , C 2 and recapture process I ’| S , C ’ 3 Sample I ’| I (the “posterior 3 3 3 2 2 predictive” distribution) 3 ’s inference is familiar, but not always easy 3 Super-Resolution via Image Recapture and Bayesian Effect Modeling 12

  13. Modeling Step Edges  Goal: preserve edges and gradients  Assumption: scenes are mostly comprised of solid objects with coherent boundaries  Capture ≈ global blur + sampling at discrete points Discrete sampling Point-spread  Scene model: a grid of linear discontinuities convolved with blurring kernels (appx. spatially varying PSF) I 00 I 01 I 02 = I 10 I 11 I 12 * Discrete I 20 I 21 I 22 sampling S Super-Resolution via Image Recapture and Bayesian Effect Modeling 13

  14. Spatially Varying Point-Spread Spatially varying point spread Dark = narrow BEI’s reconstruction 2x magnification Super-Resolution via Image Recapture and Bayesian Effect Modeling 14

  15. Scene Model: Causal or Noncausal? Hierarchical Compatibility (causal) (noncausal) Super-Resolution via Image Recapture and Bayesian Effect Modeling 15

  16. Utility of Compatibility No compatibility Compatibility Samples from prior predictive distribution I ’ No data Samples from posterior predictive distribution I ’| I Data 4x magnification Super-Resolution via Image Recapture and Bayesian Effect Modeling 16

  17. Bayesian Effect Modeling  Compatibility is an effect (noncausal)  Capture is obviously causal  Need to mix the two in the same model  Solution: use the transformation from MRFs to BNs, but locally  Confines noncausal dependence to local subgraphs  Can’t create cycles Super-Resolution via Image Recapture and Bayesian Effect Modeling 17

  18. Minimum Blur and Decimation Blur  Doing super-resolution without accounting for point- spread gives blurry results  I ’ is naturally sharpened by adding minimum blur variance in capture model and adding less in recapture  Decimation: minimum blur converging on σ = 1/3 ¼ ¼ ¼ ¼ * ••• * * * ¼ ¼ ¼ ¼ ¼ ¼ ¼ ¼ Total σ 2 = 1/9  If decimation has occurred, model it by setting minimum blur to 1/3 in capture and 1/(3 s ) in recapture Super-Resolution via Image Recapture and Bayesian Effect Modeling 18

  19. Results: Boundary Coherence Decimated (NN) BEI RS LCSR 4x magnification Super-Resolution via Image Recapture and Bayesian Effect Modeling 19

  20. Results: Edges and Gradients Original Decimated (NN) Bilinear NEDI LCSR RS BEI BEI 8x 4x magnification after two decimations Super-Resolution via Image Recapture and Bayesian Effect Modeling 20

  21. Results: Correctness Measures Super-Resolution via Image Recapture and Bayesian Effect Modeling 21

  22. Complementary Breakfast: CCD Demosaicing  Missing data problem? Rev. Bayes says it’s easy: just leave it out  In CCD demosaicing tasks, 2/3 of the data is missing: it was never collected Original Bicubic interpolation BEI’s reconstruction Super-Resolution via Image Recapture and Bayesian Effect Modeling 22

  23. Complementary Breakfast: CCD Demosaicing Original Bicubic interpolation BEI’s reconstruction Super-Resolution via Image Recapture and Bayesian Effect Modeling 23

  24. Complementary Breakfast: Inpainting and Restoration  Inpainting can be seen as a missing-data problem Defaced 33% BEI’s reconstruction  Could model defacement in the capture process Super-Resolution via Image Recapture and Bayesian Effect Modeling 24

  25. Complementary Breakfast: Inpainting and Restoration Defaced 33% BEI’s reconstruction Super-Resolution via Image Recapture and Bayesian Effect Modeling 25

  26. Limitations and Future Work  Slow: could just be Python’s fault, but there’s a lot to compute  Super-resolution’s canny ridge  Line and T-junction models  Throwing the recapture framework at every reconstruction problem that still twitches  Making Bayesian effect modeling into a graphical model in its own right Super-Resolution via Image Recapture and Bayesian Effect Modeling 26

  27. Take-Home Messages  In super-resolution (or reconstruction), make strong assumptions cuz you ain’t gettin mo data  Model capture, reconstruct scenes, recapture results  Potentially fits the actual process better  More flexible than modeling just degradation  Explicitly model what you want to reason about precisely (e.g. edges, sharpness, scenes)  Compatibility is more tractible than hierarchy and gives great results  Missing data is no problem for Bayesians Super-Resolution via Image Recapture and Bayesian Effect Modeling 27

  28. Questions ? ? Super-Resolution via Image Recapture and Bayesian Effect Modeling 28

  29. An Intriguing Equivalence Reconstruction Supervised via recapture machine learning ≡ Super-Resolution via Image Recapture and Bayesian Effect Modeling 29

  30. Details: Effect Modeling Compatibility to conditional density conversion: Joint density: Unnormalized complete conditional (Markov blanket) density: Super-Resolution via Image Recapture and Bayesian Effect Modeling 30

  31. Details: Definitions Given an m x n image I . Image coordinates are properly a parameter of the capture process C . C ’ also contains an array of coordinates. Compatibility and capture are defined in terms of nearest neighbors: Super-Resolution via Image Recapture and Bayesian Effect Modeling 31

  32. Details: Step Edges Step edge geometry is expressed as an implicit line: Facet profiles are defined by Gaussian convolution and have an analytic solution: Because of symmetry, 2D step edges can be expressed in terms of their profiles . Super-Resolution via Image Recapture and Bayesian Effect Modeling 32

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


More recommend