Non-photorealistic rendering with spot colour

Abstract

Figure 1: Spot colour in various non-photorealistic rendering styles. (a) original image (b) 3 tone rendering with spot colour (c) PhotoShop Graphic Pen rendering with spot colour (d) PhotoShop Conté Crayon rendering with spot colour (e) dithering with polygons AbstractColour is an important aspect of art. Not only does it give richness to images, but it always provides a means to highlight certain objects. This idea of spot colour has been used extensively in both fine art and commercial illustrations. Many non-photorealistic rendering (NPR) algorithms produce grayscale or monochromatic images with low saturations. In this paper we introduce the idea of spot colour to NPR and propose a simple and automatic algorithm to add spot colour to these rendering styles. The hue is thresholded into colour layers and the most appropriate layer is automatically determined based on factors such as layer region shape and salience. We also consider using an edge-based criterion to colourise the background, which is an effective means of making the foreground stand out. We demonstrate the effectiveness of our approach by adding spot colour to a diverse set of NPR styles.

When facial expressions do and do not signal minds: The role of face inversion, expression dynamism, and emotion type.

“…To create the faces’ artificial analogues, modifications were applied to the facial texture in each image or video frame (25 fps; see Rosin & Lai, 2015). This produced realistic cartoons of the same identities.…”

NPRportrait 1.0: A three-level benchmark for non-photorealistic rendering of portraits

“…• APDrawingGAN by Yi et al [39] uses a hierarchical system of generative adversarial networks (GANs) along with a line-promoting distance transform loss. • Rosin and Lai's algorithm [40] stylises the image with abstracted regions of flat colours plus black and white lines, adding skin shading and enhancing facial parts. A modified version of this pipeline renders a more abstract version inspired by the artist Julian Opie.…”

“…This section demonstrates the use of NPRportrait 1.0 to evaluate 11 NPR algorithms which cover a wide range of styles and methods: neural style transfer [37], XDoG [41], oil painting [44], pebble mosaic [45], artistic sketch method [38], APDrawingGAN [39], puppet style [40], engraving [42], hedcut [43], Julian Opie style [40], watercolour [15]. In addition, the results from analysing these stylisations allow us to confirm the requirement (detailed in Section 3) that the benchmark provides a clear range of difficulty across the three levels.…”

“…On the other hand, the Julian Opie style [40] tends to make people look more masculine and a little younger. Under the signed EMD distance, opposite sign movements (differences) cancel out, so it is useful to look at the unsigned EMD distances to check the overall discrepancy.…”

Automatic Example-Based Image Colorization Using Location-Aware Cross-Scale Matching

“…Some techniques exist that have different aims from colourising grayscale images but also bear some similarities, including colour transfer that transfers the colour styles from a reference colour image to a destination colour image (e.g. [39]), colour harmonisation that replaces colours in an image with a more aesthetically pleasing set of colours [40], and spot colour [41] where produced images are dominantly grayscale with typically compact regions containing colour. More knowledge about colourful image processing is reviewed in [42].…”