ACM Designing Interactive Systems (DIS)
Elemental Alchemist
A Generative Interface for Semantic Control of Particle Systems Across Dynamic Levels of Abstraction
Elemental Alchemist takes scene context and user intent into account to enable semantic control. It generates a contextual brush palette with scene-aware tools for applying sketch-based semantic edits. From a user’s sketch or text prompt, it generates a control panel that decomposes intent into synchronized controls across three abstraction levels: conceptual, semantic, and technical.
Editing particle-system visual effects (VFX) is vital for digital storytelling, but achieving controllable, art-directable results remains challenging due to their multi-dimensional nature. Given a large collection of parameters, users must find the ones relevant to their creative goals—a task that requires a systematic understanding of the particle system and how parameters map to high-level intents, such as making a fire look angry. Elemental Alchemist is a generative interface that transforms user intent into contextualized controls for semantic editing of particle systems. The system introduces two components: a contextual brush palette that generates tools based on scene context, and a generative control panel that surfaces relevant technical parameters and abstracts them to generate mid-level semantic attributes and high-level conceptual controls. An evaluation with 10 novice and 5 expert VFX practitioners shows the system supported users in translating high-level creative goals into particle system parameters.
Download publicationAuthors
Kyzyl Monteiro
Carnegie Mellon University
Related Publications
2026
AnimationDiff: A Visual Comparison Tool for Generated 3D Character AnimationsThis paper presents AnimationDiff, a tool for generated 3D character…
2026
Motion Generation: A Survey of Generative Approaches and BenchmarksThis research survey presents a structured review of recent motion…
2026
PointAloud: An Interaction Suite for AI-Supported Pointer-Centric Think-Aloud ComputingointAloud is a suite of novel AI-driven pointer-centric interactions…
2025
A Scalable Attention-Based Approach for Image-to-3D Texture MappingA fast transformer-based method that generates 3D textures from a…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us