Spatula: Exploring On-Demand In-Situ Interfaces and Interaction for Attribute Control

📅 2026-07-11
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Current generative authoring tools struggle to support efficient and intuitive fine-grained control over content attributes. This work proposes Spatula, a system that models attribute control as an explorable interaction landscape, automatically generating context-aware, embedded control interfaces to enable on-demand, plug-and-play attribute manipulation. Designed around four core dimensions—discoverability, precision, range, and extensibility—Spatula establishes a general-purpose framework for attribute control. A user study (N=12) demonstrates that Spatula significantly enhances the intuitiveness and flexibility of interaction, and successfully generalizes across diverse application domains, including web design and 3D modeling.
📝 Abstract
Controlling attributes is a critical step toward achieving the final creative outcome, yet current approaches fall short in supporting users in the iterative refinement of generative content. We propose Spatula, a proof-of-concept system that generates on-demand, in-situ attribute control interfaces and interactions for creating motion graphics. Building on a technical probe that automatically analyzes animation context and generates corresponding attributes and UI, we frame attribute control as an explorable landscape and explore the attribute control space along four key dimensions: Discoverability, Resolution, Scope, and Expandability. Findings from a user study (N=12) show that our system provides intuitive and convenient interactions while supporting diverse needs for fine-grained parameter control. Furthermore, our applications demonstrate that the plug-and-play design generalizes to other domains, such as web design and 3D modeling.
Problem

Research questions and friction points this paper is trying to address.

attribute control
generative content
iterative refinement
motion graphics
user interface
Innovation

Methods, ideas, or system contributions that make the work stand out.

on-demand interface
in-situ interaction
attribute control
generative content
plug-and-play design
🔎 Similar Papers
No similar papers found.