Image stylization by interactive oil paint filtering

Semmo, Amir; Limberger, Daniel; Kyprianidis, Jan Eric; Döllner, Jürgen

doi:10.1016/j.cag.2015.12.001

Cited by 39 publications

(29 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…watercolour, oil paint, pen‐and‐ink and stippling. Image filters are prominently used as building blocks of complex stylization effects, such as the bilateral filter and DoG to obtain toon renderings ( FlowAbs ), and flow‐based Gaussian smoothing for more abstract filtering that simulates oil paint [SLKD16] ( Oilpaint ). In addition, we use a Watercolor technique that simulates effects such as pigment density variation, edge darkening, wet‐in‐wet and wobbling [BKTS06, WWF*14].…”

Section: Choice Of Processing Techniquesmentioning

confidence: 99%

Reducing Affective Responses to Surgical Images and Videos Through Stylization

Besançon

Semmo

Biau

et al. 2019

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

We present the first empirical study on using colour manipulation and stylization to make surgery images/videos more palatable. While aversion to such material is natural, it limits many people's ability to satisfy their curiosity, educate themselves and make informed decisions. We selected a diverse set of image processing techniques to test them both on surgeons and lay people. While colour manipulation techniques and many artistic methods were found unusable by surgeons, edge‐preserving image smoothing yielded good results both for preserving information (as judged by surgeons) and reducing repulsiveness (as judged by lay people). We then conducted a second set of interview with surgeons to assess whether these methods could also be used on videos and derive good default parameters for information preservation. We provide extensive supplemental material at https://osf.io/4pfes/.

show abstract

Section: Choice Of Processing Techniquesmentioning

confidence: 99%

Reducing Affective Responses to Surgical Images and Videos Through Stylization

Besançon

Semmo

Biau

et al. 2019

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

show abstract

“…Related to fabrication of paintings, non‐photorealistic rendering aims to generate stylized compositions that reflect artistic intent [Bot09, BNTS07, HE04, WWF*14, LC14, CAS*97, SLKD16]. Projects about simulation of different painting media, including watercolor, create a virtual painting or investigate the properties of the media [CKIW15, LBDF13].…”

Section: Introductionmentioning

confidence: 99%

Watercolor Woodblock Printing with Image Analysis

Panotopoulou

Paris

Whiting

2018

Computer Graphics Forum

View full text Add to dashboard Cite

Watercolor paintings have a unique look that mixes subtle color gradients and sophisticated diffusion patterns. This makes them immediately recognizable and gives them a unique appeal. Creating such paintings requires advanced skills that are beyond the reach of most people. Even for trained artists, producing several copies of a painting is a tedious task. One can resort to scanning an existing painting and printing replicas, but these are all identical and have lost an essential characteristic of a painting, its uniqueness. We address these two issues with a technique to fabricate woodblocks that we later use to create watercolor prints. The woodblocks can be reused to produce multiple copies but each print is unique due to the physical process that we introduce. We also design an image processing pipeline that helps users to create the woodblocks and describe a protocol that produces prints by carefully controlling the interplay between the paper, ink pigments, and water so that the final piece depicts the desired scene while exhibiting the distinctive features of watercolor. Our technique enables anyone with the resources to produce watercolor prints.

show abstract

“…Here we mainly seek to replicate the level of abstraction targeted by the respective works: For Oilpaint, smoothing parameters with a light paint texture that fall into the medium range as described by Semmo et al [2016]; An implementation for Watercolor using flow-based bilateral filtering of FlowAbs but with wider filter kernels to achieve a similar level of abstraction as done by Bousseau et al [2006] and Wang et al [2014]; The "colorist wash" preset of BrushStrokes defined by Hertzmann [1998] to produce semi-transparent layered brush strokes; The default art map used by Praun et al [2001] that is linearly mapped to the luminance in CIE-Lab color space; And default parameters for Stippling described by Martín et al [2011] at highest resolution, with a normal distribution and black-and-white thresholding.…”

Section: Parameters and Configurationsmentioning

confidence: 99%

“…ApparentGrey [Smith et al 2008] HueShift Bilateral [Tomasi and Manduchi 1998] Kuwahara [Kyprianidis 2011] ShapeSimpl [Kang and Lee 2008] CoherenceEnh [Kyprianidis and Kang 2011] XDoG [Winnemöller et al 2012] Oilpaint [Semmo et al 2016] Watercolor [Bousseau et al 2006;Wang et al 2014] BrushStrokes [Hertzmann 1998] Hatching [Praun et al 2001] Stippling [Martín et al 2010;Martín et al 2011] [Smith et al 2008] N = 4, p i = 0.5, k i = 0.5 HueShift custom, see Section 3.5 α = 120.0 Bilateral [Tomasi and Manduchi 1998] σ d = 3.0, σ r = 4.25% FlowAbs [Kyprianidis and Döllner 2008] ρ = 2, n e = 1, n a = 3, σ d = 6, σ r = 5.25%, σ e = 1, τ = 0.99, ϵ = 0, φ e = 2, σ m = 3, q = 8, φ q = 2 Kuwahara [Kyprianidis 2011] N = 8, ρ = 2.0, r = 6, q = 8, α = 1, τ w = 0.02, p s = 0.5, p d = 1.25, τ v = 0.1 ShapeSimpl [Kang and Lee 2008] N = 8, k = 8, r = 1, etf halfw = 3, etf N = 4, σ shock = 1, τ shock = 1 CoherenceEnh [Kyprianidis and Kang 2011] N = 4, σ d = 1, τ r = 0.002, σ t = 6, σ i = 0, σ д = 1.5, r = 2, τ s = 0.005, σ a = 1.5 XDoG [Winnemöller et al 2012] σ c = 2.28, σ e = 1, σ m = 4.4, p = 99.0, φ = 100.0, ϵ = 0.65, σ a = 1.0 Stylization Oilpaint [Semmo et al 2016] σ s = 12.0, n e = 0, σ b = 12.0, k scale = 5.0, k specular = 0.8, k shininess = 12.0 Watercolor [Bousseau et al 2006;Wang et al 2014] Effects of [Bousseau et al 2006;Wang et al 2014] using FlowAbs: ρ = 2.0, σ d = 4.0, σ r = 15.00% BrushStrokes [Hertzmann 1998] [Praun et al 2001] Art map of [Praun et al 2001] scaled at 0.6, linear mapping with luminance, edge settings of FlowAbs Stippling [Martín et al 2011] r es 0 = 1200 ppi, f p = 2.0, placement randomness = 25%, distribution = normal, colors = b&w, τ = 127…”

Section: Edge-preserving Image Smoothingmentioning

confidence: 99%

“…Image filters are prominently used as building blocks of complex stylization effects, such as the bilateral filter and DoG to obtain toon renderings (FlowAbs), and flow-based Gaussian smoothing for more abstract filtering that simulates oil paint [Semmo et al 2016] (Oilpaint). In addition, we use a Watercolor technique that simulates effects such as pigment density variation, edge darkening, wet-in-wet, and wobbling [Bousseau et al 2006;Wang et al 2014].…”

Section: Image-based Artistic Renderingmentioning

confidence: 99%

See 1 more Smart Citation

Reducing affective responses to surgical images through color manipulation and stylization

Besançon

Semmo

Biau

et al. 2018

Proceedings of the Joint Symposium on Computational Aesthetics and Sketch-Based Interfaces and Modeling and Non-Photorealistic

Self Cite

View full text Add to dashboard Cite

Original photo of a lasagna dish.Output of HueShift2. Output of FlowAbs [Kyprianidis and Döllner 2008].Figure 1: Two techniques studied in this article, each using a different strategy for making surgery images easier to look at. ABSTRACTWe present the first empirical study on using color manipulation and stylization to make surgery images more palatable. While aversion to such images is natural, it limits many people's ability to satisfy their curiosity, educate themselves, and make informed decisions. We selected a diverse set of image processing techniques, and tested them both on surgeons and lay people. While many artistic methods were found unusable by surgeons, edge-preserving image smoothing gave good results both in terms of preserving information (as judged by surgeons) and reducing repulsiveness (as judged by lay people). Color manipulation turned out to be not as effective. CCS CONCEPTS• Computing methodologies → Non-photorealistic rendering; Image processing; • Human-centered computing → Empirical studies in HCI ; * Lonni Besançon is also with Linköping University, Sweden.Publication rights licensed to ACM. ACM acknowledges that this contribution was authored or co-authored by an employee, contractor or affiliate of a national government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only.

show abstract

Image stylization by interactive oil paint filtering

Cited by 39 publications

References 62 publications

Reducing Affective Responses to Surgical Images and Videos Through Stylization

Reducing Affective Responses to Surgical Images and Videos Through Stylization

Watercolor Woodblock Printing with Image Analysis

Reducing affective responses to surgical images through color manipulation and stylization

Contact Info

Product

Resources

About