Ya-Bo Huang
ABSTRACT
In the poster, we propose a model to predict the mixture of water-color pigments using convolutional neural networks (CNN). With a watercolor dataset, we train our model to minimize the loss function of sRGB differences. In metric of color difference ΔELab, our model achieves 88.7 % of data that ΔELab < 5 on the test set, which means the difference can not easily be detected by human eye. In addition, an interesting phenomenon is found; Even if the reflectance curve of the predicted color is not as smooth as the ground truth curve, the RGB color is still close to the ground truth.
Supplemental Material
Available for Download
Supplemental files.
- William Baxter, Jeremy Wendt, and Ming C Lin. 2004. IMPaSTo: a realistic, interactive model for paint. In Proc. of the 3rd international symposium on Non-photorealistic animation and rendering. ACM, 45--148. Google Scholar
Digital Library
- Mei-Yun Chen, Ci-Syuan Yang, and Ming Ouhyoung. 2018. A Smart Palette for Helping Novice Painters to Mix Physical Watercolor Pigments. In Proc. of EuroGraphics 2018, Posters,, Eakta Jain and Jirí Kosinka (Eds.). The Eurographics Association, April 2018.Google Scholar
- Per Edström. 2007. Examination of the revised Kubelka-Munk theory: considerations of modeling strategies. JOSA A 24, 2 (2007), 548--556.Google ScholarCross Ref
- Chet S Haase and Gary W Meyer. 1992. Modeling pigmented materials for realistic image synthesis. ACM Transactions on Graphics (TOG) 11, 4 (1992), 305--335. Google ScholarDigital Library
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proc. of the IEEE conference on computer vision and pattern recognition. 770--778.Google ScholarCross Ref
- Paul Kubelka. 1948. New contributions to the optics of intensely light-scattering materials. Part I. Josa 38, 5 (1948), 448--457.Google ScholarCross Ref
Index Terms
Perceptual-based CNN model for watercolor mixing prediction
Recommendations
Practical pigment mixing for digital painting
There is a significant flaw in today's painting software: the colors do not mix like actual paints. E.g., blue and yellow make gray instead of green. This is because the software is built around the RGB representation, which models the mixing of colored ...
Pigment-based recoloring of watercolor paintings
NPAR '17: Proceedings of the Symposium on Non-Photorealistic Animation and RenderingThe color palette used by an artist when creating a painting is an important tool for expressing emotion, directing attention, and more. However, choosing a palette is an intricate task that requires considerable skill and experience. In this work, we ...
Modeling pigmented materials for realistic image synthesis
This article discusses and applies the Kubelka-Munk theory of pigment mixing to computer graphics in order to facilitate improved image synthesis. The theories of additive and subtractive color mixing are discussed and are shown to be insufficient for ...
Comments