Structure-preserving manipulation of photographs

Visual content is often better communicated by simpliﬁed or exaggerated images than by the "real world like" images. In this paper, we offer a tool for creating such enhanced representations of photographs in a way consistent with the original image content. To do so, we develop a method to identify the relevant image strucures and their importance. Our approach (a) uses edges as the basic structural unit in the image, (b) proposes tools to manipulate this structure in a ﬂexible way, and (c) employs gradient domain image processing techniques to reconstruct the ﬁnal image from a "cropped" gradient information. This edge-based approach to non-photorealistic image processing is made feasible by two new techniques we introduce: an addition to the Gaussian scale space theory to compute a perceptually meaningful hierarchy of structures, and a contrast estimation method necessary for faithful gradient-based reconstructions. We ﬁnally present various applications that manipulate image structure in different ways.

Keywords

visual communication multiscale analysis image processing image reconstruction

Domains

Graphics [cs.GR]

Fichier principal

photo_manipulation_npar2007.pdf (15.65 Mo)

bee_mask.jpg (145.86 Ko)

bee_teaser.jpg (470.98 Ko)

matlab_cleaned/best_scale.m (793 B)

matlab_cleaned/dilate.m (1.61 Ko)

matlab_cleaned/distance_dilate.m (4.15 Ko)

matlab_cleaned/dst.m (933 B)

matlab_cleaned/gaussgradient.m (1.17 Ko)

matlab_cleaned/level_detail_blur.m (5.28 Ko)

matlab_cleaned/lmax.m (382 B)

matlab_cleaned/make_scale_spaces.m (1.7 Ko)

matlab_cleaned/poisson_solver_function.m (1.89 Ko)

matlab_cleaned/readme.txt (154 B)

matlab_cleaned/scaleSpaceMain.m (303 B)

matlab_cleaned/scale_map_canny.m (1.18 Ko)

matlab_cleaned/scale_space_canny.m (508 B)

matlab_cleaned/scale_space_deriv.m (1.32 Ko)

matlab_cleaned/scale_space_link.m (1.82 Ko)

photo_manipulation_color_plate.pdf (7.08 Mo)

reblur.jpg (258.89 Ko)

structure_preserv_photo_manip/best_scale.m (1.09 Ko)

structure_preserv_photo_manip/dilate.m (1.61 Ko)

structure_preserv_photo_manip/distance_dilate.m (4.15 Ko)

structure_preserv_photo_manip/dst.m (933 B)

structure_preserv_photo_manip/gaussgradient.m (1.17 Ko)

structure_preserv_photo_manip/idst.m (448 B)

structure_preserv_photo_manip/level_detail_blur.m (5.37 Ko)

structure_preserv_photo_manip/lmax.m (382 B)

structure_preserv_photo_manip/make_scale_spaces.m (1.73 Ko)

structure_preserv_photo_manip/poisson_solver_function.m (1.89 Ko)

structure_preserv_photo_manip/readme.txt (124 B)

structure_preserv_photo_manip/scale_map_canny.m (1.18 Ko)

structure_preserv_photo_manip/scale_space_canny.m (513 B)

structure_preserv_photo_manip/scale_space_deriv.m (1.32 Ko)

structure_preserv_photo_manip/scale_space_link.m (1.82 Ko)

style.jpg (316.57 Ko)

Origin : Files produced by the author(s)

Format : Figure, Image

Format : Other

Format : Figure, Image

Format : Other

Format : Figure, Image

Pascal Barla : Connect in order to contact the contributor

https://inria.hal.science/inria-00362868

Submitted on : Friday, April 29, 2011-10:26:35 AM

Last modification on : Thursday, April 4, 2024-9:07:11 PM

Long-term archiving on: Saturday, July 30, 2011-2:24:28 AM

Dates and versions

inria-00362868 , version 1 (29-04-2011)

Identifiers

HAL Id : inria-00362868 , version 1
DOI : 10.1145/1274871.1274888

Cite

Alexandrina Orzan, Adrien Bousseau, Pascal Barla, Joëlle Thollot. Structure-preserving manipulation of photographs. International Symposium on Non-Photorealistic Animation and Rendering (NPAR), Aug 2007, San Diego, United States. pp.103-110, ⟨10.1145/1274871.1274888⟩. ⟨inria-00362868⟩

Export

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

UNIV-RENNES1 UGA CNRS INRIA IRISA LJK LJK_GI LJK_GI_ARTIS INRIA2 UR1-MATH-STIC UR1-UFR-ISTIC UNIV-RENNES UR1-MATH-NUM

418 View

530 Download