Aug 2026· Proceedings of the 14th ACM SIGPLAN International Workshop on Functional Art, Music, Modelling, and Design· pp. 43-46· 0 citations· 1 references
TL;DR
This work develops a framework in JavaScript to create a drawing algorithm that draws visual artworks in the style of visionary artist Piet Mondrian and contemporary artist Adam Lister.
Abstract
We developed a framework in JavaScript for procedurally generating visual artworks and music. This framework specifies how drawing algorithms are structured to step-by-step create images. While images are being generated, drawing actions are (optionally) converted to sounds to create music. Drawing algorithms are treated as objects that carry a state that changes over time. The current state determines how the next drawing step adds to and manipulates the image canvas. Drawing algorithms can run independent of each other with a collection of premade functionalities such as initialize, start, pause, reset, and drawOneStep. In addition, drawing algorithms can be passed as input into functions allowing them to run under a variety of configurations and be connected to user interfaces and external applications. Furthermore, using this framework, we present a particularly interesting example of a drawing algorithm that has a dual purpose for both visually representing solutions to an algorithmic problem and for creating unique artworks. This algorithmic problem is defined as follows. Given an m by n binary matrix, our task is to enumerate all rectangular blocks containing only 1 entries on the border and 0 entries within the interior. The authors previously developed a solution for this problem that runs in O(m · n) time using O(n) space. We adapt this solution to create a drawing algorithm that draws visual artworks in the style of visionary artist Piet Mondrian and contemporary artist Adam Lister.
There is growing interest in using pretrained machine learning models for non-photorealistic rendering and sketch synthesis. However, existing approaches typically rely on differentiable rendering, which can be constraining for artists working with algorithmic processes and mechanical plotters. This pictorial introduces a gradient-free, artist-centred method for synthesising sketches from text prompts, designed for use with a plotter. Drawing gestures are parameterised as implicit neural representations and optimised using an evolution strategy, with semantic guidance from CLIP, a vision-language model. The system runs locally on laptops and provides real-time visual feedback for artistic iteration. Its gradient-free design enables flexible, non-differentiable rendering pipelines implemented in the browser using familiar JavaScript graphics toolkits. An early version was exhibited in 2025 during a group exhibition in Tokyo, functioning both as an artwork and a research-through-art investigation into how machine learning systems might better align with artists’ practices.
Matt DesLauriers· Creativity & Cognition· 0 citations
Developing the look of GOAT required us to analyze stylized painted reference art, translate it into a visual language for 3D animation, and create a scalable workflow for a large team of artists with varied experience levels, while maintaining the desired level of artistic quality. We used the toolsets developed on previous shows [Davignon and Clair 2023] and worked with the team to create new tools that could solve problems unique to the look of GOAT. We break down the visual style and match its components with plug and play modules that artists can dial to taste. All modules are collected in a show library, equipping artists to tackle any problem they might face. The template starts with a very basic, procedural setup and allows artists to build upon it by adding snippets and modules. This approach allowed us to stay agile, address a wide variety of challenges with a small number of toolsets, and keep our look consistent throughout the film.
Megan Deane, Rebecca J. Lin· Proceedings of the Special I...· 0 citations
The goal is not to present AI as a replacement for artists, but to show how controllable AI systems can support more precise, collaborative, and extensible forms of creative production.
Zheng Wei, Yuying Tang, Mia Tang et al.· Proceedings of the Special I...· 0 citations
Another DSL for pictures? Seems fishy. But hold fast as we chart a course to an embedded DSL for the domain of slide presentations with animations. Our DSL programs interact with the host language in two ways: by allowing pictures and animations to be built using host-language functions (resembling a shallow embedding), and by allowing host-language reflection on their construction (resembling a deep embedding). As a result, users can define their own animation combinators but still also inspect, adjust, and reassemble animations. To demonstrate our DSL's expressive power, we show how it supports a Keynote-like Magic Move operation. Having made the DSL shipshape, we dive into a lesson learned about deep and shallow DSL design. While deep and shallow may seem like mutually exclusive options, we argue they are actually points on an entire spectrum of possible DSL designs. More importantly, our paper demonstrates that points on the spectrum between deep and shallow are where DSL designs achieve full sail.
Oliver Flatt, R. Findler, M. Flatt· Proceedings of the ACM on Pr...· 0 citations
Artistic charts combine data visualization with expressive marks, textures, and typography, but they are difficult for image generators: an output is useful only when its stylization preserves chart geometry, exact in-image text, and the semantic binding between labels and marks. We introduce ArtChart, a framework for faithful artistic chart generation with integrated text rendering. Given a structured chart specification and an artistic prompt, ArtChart first renders a text-free grayscale layout that encodes the target chart geometry, then trains a chart-specific control module to preserve mathematical structure. To address the remaining text and layout errors, we further refine the generation policy through GRPO-based reinforcement learning with OCR-based text rewards, VLM-based layout rewards, and aesthetic rewards. A multi-expert distillation stage reconciles these objectives by distilling single-reward experts into one balanced generation policy. We also construct ArtChart-Bench, a bilingual 2K-prompt benchmark covering four chart types, controlled value distributions, diverse label/value formats, and 15 artistic styles, together with ArtChart-Eval, a six-axis evaluation protocol measuring mathematical logic, text accuracy, text layout, aesthetics, instruction following, and readability. Experiments on ArtChart-Bench show that ArtChart consistently outperforms prompt-only, image-editing, and generic ControlNet baselines, with the largest gains on mathematical fidelity and label-layout binding while maintaining competitive visual quality. These results suggest that artistic chart generation should be evaluated as reliable visual communication rather than as generic stylized image synthesis.
Meijia Huang, Yingjie Yin, Shihao Wang et al.· 0 citations
Procedural generation is widely applied, from accelerating development of large and detailed virtual worlds to providing highly varied game content during gameplay. However, for procedural generators to be widely adopted, developers and artists must be able to select a suitable approach and contextualize it with respect to artifact design objectives. This paper presents an overview of the four main procedural generation approaches: constructive, search-based, solver-based, and machine learning. The paper also introduces three lenses for understanding how to use procedural generators in practice: benefits, capabilities, and usability. The benefits lens examines what objectives can be achieved with procedural generators. The capabilities lens distinguishes between artist-assisting procedural generation tools, procedural materials, automated designers, and expert systems capable of generating reliable artifacts. Finally, the usability lens addresses how to integrate procedural generators into practice and how users interact with them. Examples of generation approaches from academia and commercial works are provided to illustrate each lens. This review synthesizes the characteristics, benefits and drawbacks of various procedural generation methods, helping developers choose the most appropriate technique based on a particular use case. A decision support matrix is also provided to illustrate how to apply this practical view in different development scenarios.
Robert Andrei Caragicu, Anca Morar, A. Moldoveanu et al.· IEEE Access· 0 citations