Interactive image completion with perspective correction

Pavić, Darko; Schönefeld, Volker; Kobbelt, Leif

doi:10.1007/s00371-006-0050-2

Cited by 65 publications

(43 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several authors (Pavić et al, 2006;Huang et al, 2013) have addressed this issue using some user interaction to guide the search process. For example, the user provides information about the symmetries in the image, or specifies 3D planes which are then used for rectification and the rectified planes in turn are used for searching for correspondences.…”

Section: Related Workmentioning

confidence: 99%

Affine Invariant Self-similarity for Exemplar-based Inpainting

Fedorov

Arias

Facciolo

et al. 2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

View full text Add to dashboard Cite

Abstract:This paper presents a new method for exemplar-based image inpainting using transformed patches. We build upon a recent affine invariant self-similarity measure which automatically transforms patches to compare them in an appropriate manner. As a consequence, it intrinsically extends the set of available source patches to copy information from. When comparing two patches, instead of searching for the appropriate patch transformation in a highly dimensional parameter space, our approach allows us to determine a single transformation from the texture content in both patches. We incorporate the affine invariant similarity measure in a variational formulation for inpainting and present an algorithm together with experimental results illustrating this approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Affine Invariant Self-similarity for Exemplar-based Inpainting

Fedorov

Arias

Facciolo

et al. 2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

View full text Add to dashboard Cite

show abstract

“…This however strongly restricts the search space. Often the user is asked to identify how square regions get mapped into the final image [IBG03,LLH04,PSK06], typically by overlaying a distorted lattice over the photograph. This is used to re-project a flat synthesis result into the image, giving the illusion it was generated with the appropriate distortion.…”

Section: Related Workmentioning

confidence: 99%

“…A key issue is that the primitives should have a reasonably low number or degrees of freedom to allow easy interaction, yet be powerful enough to describe planar and curved surfaces under projection. Planar geometry: In the planar case we build on the 2D homography approach of Pavić et al [PSK06]. The user places four corner points to define a 2D homography between the DES and a flat rectangle.…”

Section: User Interfacementioning

confidence: 99%

“…Previous UIs attempt to lessen such distortions using very fine grids [LLH04,PSK06]. However, placing that many nodes is tedious for the user, especially for textures that provide few visible clues for their placement.…”

Section: User Interfacementioning

confidence: 99%

“…the first derivative. C 0 continuity is always maintained and no relaxation algorithm [PSK06] needs to be applied to recover from imprecise user input. Our patches can overlap, be disjoint, and may in general not perfectly match.…”

Section: User Interfacementioning

confidence: 99%

See 2 more Smart Citations

Texture Synthesis From Photographs

Eisenacher

Lefèbvre

Stamminger

2008

Computer Graphics Forum

View full text Add to dashboard Cite

The goal of texture synthesis is to generate an arbitrarily large high-quality texture from a small input sample. Generally, it is assumed that the input image is given as a flat, square piece of texture, thus it has to be carefully prepared from a picture taken under ideal conditions. Instead we would like to extract the input texture from any surface from within an arbitrary photograph. This introduces several challenges: Only parts of the photograph are covered with the texture of interest, perspective and scene geometry introduce distortions, and the texture is non-uniformly sampled during the capture process. This breaks many of the assumptions used for synthesis. In this paper we combine a simple novel user interface with a generic per-pixel synthesis algorithm to achieve high-quality synthesis from a photograph. Our interface lets the user locally describe the geometry supporting the textures by combining rational Bézier patches. These are particularly well suited to describe curved surfaces under projection. Further, we extend per-pixel synthesis to account for arbitrary texture sparsity and distortion, both in the input image and in the synthesis output. Applications range from synthesizing textures directly from photographs to high-quality texture completion.

show abstract

Pixel2Field: Single Image Transformation to Physical Field of Sports Videos

Peng

2019

Advances in Visual Computing

View full text Add to dashboard Cite

Interactive image completion with perspective correction

Cited by 65 publications

References 28 publications

Affine Invariant Self-similarity for Exemplar-based Inpainting

Affine Invariant Self-similarity for Exemplar-based Inpainting

Texture Synthesis From Photographs

Pixel2Field: Single Image Transformation to Physical Field of Sports Videos

Contact Info

Product

Resources

About