Video Stippling

Abstract

In this paper, we consider rendering color videos using a non-photo-realistic art form technique commonly called stippling. Stippling is the art of rendering images using point sets, possibly with various attributes like sizes, elementary shapes, and colors. Producing nice stippling is attractive not only for the sake of image depiction but also because it yields a compact vectorial format for storing the semantic information of media. Moreover, stippling is by construction easily tunable to various device resolutions without suffering from bitmap sampling artifacts when resizing. The underlying core technique for stippling images is to compute a centroidal Voronoi tessellation on a well-designed underlying density. This density relates to the image content, and is used to compute a weighted Voronoi diagram. By considering videos as image sequences and initializing properly the stippling of one image by the result of its predecessor, one avoids undesirable point flickering artifacts and can produce stippled videos that nevertheless still exhibit noticeable artifacts. To overcome this, our method improves over the naive scheme by considering dynamic point creation and deletion according to the current scene semantic complexity, and show how to effectively vectorize video while adjusting for both color and contrast characteristics. Furthermore, we explain how to produce high quality stippled "videos" (eg., fully dynamic spatio-temporal point sets) for media containing various fading effects, like quick motions of objects or progressive shot changes. We report on practical performances of our implementation, and present several stippled video results rendered on-the-fly using our viewer that allows both spatio-temporal dynamic rescaling (eg., upscale vectorially frame rate).

Multi-class inverted stippling

“…Color Stippling. Existing color stippling works [Houit and Nielsen 2011;Jang and Hong 2005;Ma et al 2019] typically use black-andwhite stippling methods followed by coloring each dot. Another straightforward approach uses error diffusion [Floyd and Steinberg 1976] to color the stipples from a black-and-white stippled result.…”

Tile art image generation using parallel greedy algorithm on the GPU and its approximation with machine learning

“…In this work, to obtain high-quality tile art images, we generate a tile art image such that the total error is minimized, while several studies, which tackle tile art image generation, consider features in the original image such as edges and directions of gradation. [10][11][12] Unlike these studies, our proposed approach can represent such features without any image feature extraction techniques. In the greedy approach, we adopt the greedy search technique.…”