ACM Designing Interactive Systems (DIS)
AnimationDiff
A Visual Comparison Tool for Generated 3D Character Animations
AnimationDiff for evaluation and comparison of generated 3D character animations. (a) Scene controls enable users to contextualize the animations in camera and scene. (b) Camera Lenses enable users to switch between comparison modes. (c) Playback controls enable control which and how animations are played in the scene. (d) Spatial Lenses visualize and filter spatial information in the scene. (e) Temporal Lenses give an overview of animations over time for skimming and quick comparison.
Creating 3D character animations traditionally requires significant time and effort from the animator. Advancements in generative methods now enable easy creation of multiple character animation variations for use or further editing. However, this capability introduces a new challenge in comparing character animations to select the best animation, which is challenging due to temporal misalignment and the large amount of spatial data. We present AnimationDiff, a visual comparison tool for generated character animations. AnimationDiff enables contextual comparisons in the intended scene and camera angle, and embedding of spatial information by combining established animation visualization techniques and easy switching between overlaid and side-by-side comparisons. AnimationDiff also supports filtering to handle information overload, and Temporal Lenses that visualize entire animations over time for overview, alignment, and comparison. We evaluated AnimationDiff in a user study, showcasing its efficacy in animation comparison and providing design insights for comparing motion.
Download publicationAuthors
Related Publications
2026
Elemental Alchemist: A Generative Interface for Semantic Control of Particle Systems Across Dynamic Levels of AbstractionThis paper explores Elemental Alchemist, taking scene context and user…
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…
2024
Wavelet Latent Diffusion: Billion-Parameter 3D Generative Model with Compact Wavelet EncodingsAddressing a common limitation of generative AI models, WaLa encodes…
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