Local Laplacian Filters: Edge-aware Image Processing with a - - PowerPoint PPT Presentation

▶
local laplacian filters edge aware image processing with
SMART_READER_LITE
LIVE PREVIEW

Local Laplacian Filters: Edge-aware Image Processing with a - - PowerPoint PPT Presentation

May 22, 2023 315 likes •632 views

Local Laplacian Filters: Edge-aware Image Processing with a Laplacian Pyramid Paper by Sylvain Paris, Samuel W. Hasinoff, Jan Kautz Presenter: Jing Niu An Example Input: Milestones and Advances in Image Analysis WS 12/13 2 An Example

slide-1
SLIDE 1

Paper by Sylvain Paris, Samuel W. Hasinoff, Jan Kautz Presenter: Jing Niu

Local Laplacian Filters: Edge-aware Image Processing with a Laplacian Pyramid

slide-2
SLIDE 2

Milestones and Advances in Image Analysis WS 12/13 2

An Example

  • Input:
slide-3
SLIDE 3

Milestones and Advances in Image Analysis WS 12/13 3

An Example

  • output
slide-4
SLIDE 4

Milestones and Advances in Image Analysis WS 12/13 4

Outline

  • Motivation
  • Laplacian Pyramids
  • Local Laplacian Filtering
  • Algorithm
  • Applications
slide-5
SLIDE 5

Milestones and Advances in Image Analysis WS 12/13 5

Motivation

  • Belived to be unsuitable for:
  • Representing edges
  • Edge-aware operations (edge-preserving smoothing, tone

mapping)

  • Reason:

– Build upon isotropic, spatially invariant gaussian kernel

  • Goal:
  • Flexible approach
  • edge-aware image processing using

– simple point-wise manipulation of Laplacian pyramids

slide-6
SLIDE 6

Milestones and Advances in Image Analysis WS 12/13 6

Laplacian and Guassian Pyramids

  • Gaussian Pyramid:
  • A set of image levels
  • Represent lower resolution
  • High frequency details disappear

upsample subsample

slide-7
SLIDE 7

Milestones and Advances in Image Analysis WS 12/13 7

Laplacian Pyramid

  • Downsampling:decomposition

G0 G2 G1 L1 L0

Ref[1] Residual

slide-8
SLIDE 8

Milestones and Advances in Image Analysis WS 12/13 8

Laplacian Pyramid

  • Upsampling:

G1 L0 G0 L1 G2

Ref[1]

slide-9
SLIDE 9

Milestones and Advances in Image Analysis WS 12/13 9

Local Laplacian Filtering

  • Range compression and clipping

Input Signal

slide-10
SLIDE 10

Milestones and Advances in Image Analysis WS 12/13 10

Local Laplacian Filtering

  • Range compression and clipping

Right clippling Input Signal

slide-11
SLIDE 11

Milestones and Advances in Image Analysis WS 12/13 11

Local Laplacian Filtering

  • Range compression and clipping

Right clippling Input Signal

slide-12
SLIDE 12

Milestones and Advances in Image Analysis WS 12/13 12

Local Laplacian Filtering

  • Range compression and clipping

Left Clipping

Right clipping

Input Signal

slide-13
SLIDE 13

Milestones and Advances in Image Analysis WS 12/13 13

Local Laplacian Filtering

  • Range compression and clipping

Right clipping Left clipping

Input Signal merged

slide-14
SLIDE 14

Milestones and Advances in Image Analysis WS 12/13 14

Point-wise Remapping function

edge--aware detail manipulation detail smoothing detail enhancement edge--aware tone manipulation tone mapping inverse tone mapping combined operator detail enhance + tone map

slide-15
SLIDE 15

Milestones and Advances in Image Analysis WS 12/13 15

An overview of the algorithm

Approach: construct laplacian pyramid of filtered output

slide-16
SLIDE 16

Milestones and Advances in Image Analysis WS 12/13 16

Illustration

slide-17
SLIDE 17

Milestones and Advances in Image Analysis WS 12/13 17

Illustration

slide-18
SLIDE 18

Milestones and Advances in Image Analysis WS 12/13 18

Illustration

slide-19
SLIDE 19

Milestones and Advances in Image Analysis WS 12/13 19

Illustration

slide-20
SLIDE 20

Milestones and Advances in Image Analysis WS 12/13 20

Illustration

slide-21
SLIDE 21

Milestones and Advances in Image Analysis WS 12/13 21

Illustration

slide-22
SLIDE 22

Milestones and Advances in Image Analysis WS 12/13 22

Illustration

slide-23
SLIDE 23

Milestones and Advances in Image Analysis WS 12/13 23

Application

  • Detail manipulation
  • Tone mapping
slide-24
SLIDE 24

Milestones and Advances in Image Analysis WS 12/13 24

Application

  • Detail manipulation
  • Tone mapping

β, σr similar effects on tone mapping results α is set to 1

slide-25
SLIDE 25

Milestones and Advances in Image Analysis WS 12/13 25

More Results

bilateral filter and close up Our result and close up

slide-26
SLIDE 26

Milestones and Advances in Image Analysis WS 12/13 26

More Results

slide-27
SLIDE 27

Milestones and Advances in Image Analysis WS 12/13 27

Conclusion

  • Edge aware
  • Based solely on laplacian pyramid
  • Simple method
  • Robustness
  • Artifact-free
  • high quality image
  • open new perspectives on multi-scale image

analysis and editing

slide-28
SLIDE 28

Milestones and Advances in Image Analysis WS 12/13 28

Reference

  • Pyramid-based Image Synthesis Theory

Shuguang Mao and Morgan Brown

  • Advanced Image Analysis Christian Schmaltz
  • Local Laplacian Filters: Edge-aware Image Processing

with a Laplacian Pyramid

Sylvain Paris, Samuel W. Hasinoff, Jan Kautz

slide-29
SLIDE 29

Milestones and Advances in Image Analysis WS 12/13 29

Thank you