Cross Dissolve Without Cross Fade: Preserving Contrast, Color and Salience in Image Compositing

Grundland, Mark; Vohra, Rahul; Williams, Gareth; Dodgson, Neil A.

doi:10.1111/j.1467-8659.2006.00977.x

Cited by 44 publications

(23 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We plan to address this limitation in future work. One possible solution would be to replace the linear blending by a salience aware blending in the spirit of the work of Grundland et al [2006]. This blending should better preserve the relevant features of the texture.…”

Section: Discussion and Future Workmentioning

confidence: 99%

Dynamic solid textures for real-time coherent stylization

Bénard

Bousseau

Thollot

2009

Proceedings of the 2009 Symposium on Interactive 3D Graphics and Games

View full text Add to dashboard Cite

Figure 1: Dynamic solid textures (on the left) serve as a basis to create a large range of temporally coherent styles. From left to right: a complex scene (538k tris) is rendered in real-time in a watercolor style, a collage style and a binary style. AbstractStylized rendering methods, which aim at depicting 3D scenes with 2D marks such as pigments or strokes, are often faced with temporal coherence issues when applied to dynamic scenes. These issues arise from the difficulty of having to satisfy two contrary goals: ensuring that the style marks follow 3D motions while preserving their 2D appearance. In this paper we describe a new texture based method for real-time temporally coherent stylization called dynamic textures. A dynamic texture is a standard texture mapped on the object and enriched with an infinite zoom mechanism. This simple and fast mechanism maintains quasi-constant size and density of texture elements in screen space for any distance from the camera. We show that these dynamic textures can be used in many stylization techniques, enforcing the 2D appearance of the style marks while preserving the accurate 3D motion of the depicted objects.Although our infinite zoom technique can be used with both 2D or 3D textures, we focus in this paper on the 3D case (dynamic solid textures) which avoids the need for complex parameterizations of 3D surfaces. This makes dynamic textures easy to integrate in existing rendering pipelines with almost no loss in performance, as demonstrated by our implementation in a game rendering engine.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

Dynamic solid textures for real-time coherent stylization

Bénard

Bousseau

Thollot

2009

Proceedings of the 2009 Symposium on Interactive 3D Graphics and Games

View full text Add to dashboard Cite

show abstract

“…The weight can be determined by either radial basis function [4] or a power function of contrast, saturation and well-exposedness. Do we consider the creation of a high-contrast image as a problem of image-composition, then we not only can improve on exposure, but also on sharpness and the depth of field [7,5].…”

Section: Related Workmentioning

confidence: 99%

Multi-Exposure Document Fusion Based on Edge-Intensities

Block

Maxim

Wiesel

et al. 2009

2009 10th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

This paper presents a new algorithm for fusioning images of text-documents taken with different exposures. It is compared to several standard block oriented exposure-and focus-blending-algorithms. The recognition rate of a publicly available OCR-engine is used as a benchmark to quantify the results. Experiments show in average an improvement in the recognition rate from 0.46 to 0.64 by employing exposure blending as preprocessing step to an OCR. The presented algorithm of blending high-pass filtered images instead of original images further increases the recognition rate to 0.95.

show abstract

“…At some point the association of features with input images becomes too hard and the blend loses its usefulness. In addition, as the number of images in the blend increases, the contrast problem highlighted by Grundland et al (2006) becomes increasingly significant. If we are blending three images the mid-blend image will be constructed from three images, each having one-third contrast.…”

Section: Using the Blendersmentioning

confidence: 99%