1 / 77

Transferring Color to Greyscale Images

Transferring Color to Greyscale Images. Tomihisa (Tom) Welsh Michael Ashikhmin Klaus Mueller. Center for Visual Computing Stony Brook University. The Problem. How to colorize greyscale images?. The Problem. How to colorize greyscale images?. The Problem.

fcha
Télécharger la présentation

Transferring Color to Greyscale Images

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Transferring Color to Greyscale Images Tomihisa (Tom) Welsh Michael Ashikhmin Klaus Mueller Center for Visual Computing Stony Brook University

  2. The Problem • How to colorize greyscale images?

  3. The Problem • How to colorize greyscale images?

  4. The Problem • How to colorize greyscale images? • Is his tie blue or green?

  5. The Problem • How to colorize greyscale images? • Red!!

  6. The Problem • How to colorize greyscale images? • Issues: • No “correct” solution • Need to be creative • How to minimize the manual labor involved?

  7. Motivation • Enhance Scientific Data • Medical Imaging (MRI, CT, X-Ray)

  8. Motivation • Enhance Scientific Data • Medical Imaging (MRI, CT, X-Ray) • Satellite Images (Landsat)

  9. Motivation • Enhance Scientific Data • Medical Imaging (MRI, CT, X-Ray) • Satellite Images (Landsat) • Scanning Electron Microscopy (SEM)

  10. Motivation • Enhance Scientific Data • Medical Imaging (MRI, CT, X-Ray) • Satellite Images (Landsat) • Scanning Electron Microscopy (SEM) • Colorize black/white photographs and movies

  11. Motivation • Enhance Scientific Data • Medical Imaging (MRI, CT, X-Ray) • Satellite Images (Landsat) • Scanning Electron Microscopy (SEM) • Colorize black/white photographs and movies • Artistic Effects

  12. The Task • The problem is fundamentally ill-posed • It is an attempt to extrapolate from 1-D to 3-D • Map scalar luminance (intensity) to vector RGB

  13. Previous Methods • Coloring Book Method • Photoshop: manually paint color with low opacity

  14. Previous Methods • Coloring Book Method • Photoshop: manually paint color with low opacity • Movie Industry: track polygons [Cinesite Press Article]

  15. Previous Methods • Coloring Book Method • Photoshop: manually paint color with low opacity • Movie Industry: track polygons [Cinesite Press Article] • Pseudo-coloring • Global Transformation/Color Map

  16. Previous Methods • Coloring Book Method • Photoshop: manually paint color with low opacity • Movie Industry: track polygons [Cinesite Press Article] • Pseudo-coloring • Global Transformation/Color Map • Satellite Images • Registration [R2V Software], Orthoimagery [Premoze]

  17. Previous Methods • Coloring Book Method • Photoshop: manually paint color with low opacity • Movie Industry: track polygons [Cinesite Press Article] • Pseudo-coloring • Global Transformation/Color Map • Satellite Images • Registration [R2V Software], Orthoimagery [Premoze] • Image Analogies • Grey Source : Color Source :: Grey Target : Result

  18. Related Work • “Color Transfer between Images” [Reinhard et al. 2001]

  19. Related Work • “Color Transfer between Images” [Reinhard et al. 2001] + Source Target

  20. Related Work • “Color Transfer between Images” [Reinhard et al. 2001] + = Source Final Target

  21. Reinhard et al. • Decorrelated color space (lαβ) [Ruderman et al., 1998] • Scale and shift color distributions globally (Using mean and standard deviation) Target Source

  22. Reinhard et al. • Decorrelated color space (lαβ) [Ruderman et al., 1998] • Scale and shift color distributions globally (Using mean and standard deviation) Target (Scaled) Source

  23. Reinhard et al. • Decorrelated color space (lαβ) [Ruderman et al., 1998] • Scale and shift color distributions globally (Using mean and standard deviation) Target (Scaled & Shifted) Source

  24. Our Approach Target

  25. ??? Our Approach Target • Select color source image Source + ???

  26. Our Approach Target • Select color source image • Match each target pixel with a few sourcepixels Source +

  27. Our Approach Target • Select color source image • Match each target pixel with a few sourcepixels • Choose best match using local pixel neighborhood statistics Source +

  28. Our Approach Target • Select color source image • Match each target pixel with a few sourcepixels • Choose best match using local pixel neighborhood statistics • Transfer color Source + =

  29. Our Approach Target Final • Select color source image • Match each target pixel with a few sourcepixels • Choose best match using local pixel neighborhood statistics • Transfer color • Repeat for all pixels Source + =

  30. Global Image Matching Procedure • Convert images to lαβ color space • Image Matching • Color Transfer

  31. 1. Convert to lαβ Space • Luminance (l), alpha (α) and beta (β) channels • Minimizes correlation between axes (i.e. cross-channel artifacts) Color Image RGB lαβ

  32. 2. Image Matching • Remap luminance histograms between src/target Source-Before Target Source-After

  33. 2. Image Matching • Remap luminance histograms between src/target • Precompute neighborhood statistics for images

  34. 2. Image Matching • Remap luminance histograms between src/target • Precompute neighborhood statistics for images • Reduce samples using jittered sampling - Faster computation due to smaller search space

  35. 2. Image Matching • Remap luminance histograms between src/target • Precompute neighborhood statistics for images • Reduce samples using jittered sampling - Faster computation due to smaller search space

  36. 2. Image Matching • Remap luminance histograms between src/target • Precompute neighborhood statistics for images • Reduce samples using jittered sampling - Faster computation due to smaller search space

  37. 2. Image Matching • Remap luminance histograms between src/target • Precompute neighborhood statistics for images • Reduce samples using jittered sampling - Faster computation due to smaller search space • Find best neighborhood match from samples - Weighted metric of luminance, mean, standard deviation

  38. 3. Color Transfer • Transfer only alpha and beta channels (color) Target Image Colorized Results

  39. 3. Color Transfer • Transfer only alpha and beta channels (color) • The original luminance value remains unchanged Target Image Colorized Results Convert to Greyscale (Photoshop)

  40. Results: satellite + Source Target

  41. Results: satellite + = Source Target Final

  42. Results: Textures + Source Target

  43. Results: Textures + = Source Target Final

  44. Limitations (Global Approach) + = Source Target Final

  45. Limitations (Global Approach) + = + = Source Target Final

  46. Limitations (Global Approach) + = + = Source Target Final

  47. User-Assisted Approach • User selects small number of swatches • Transfer color only to swatches (Global Matching Procedure) • Color entire target image (Only use swatch samples)

  48. 1. Selection of Swatches Source Target

  49. 2. Transfer Color to Swatches • Transfer color using Global Matching Procedure (described previously)

  50. 3. Colorize Entire Image • Discard original source image

More Related