Key points
- Enables iterative natural language editing of character animation via kinematic motion operators.
- Operators are aligned with animator vocabulary and editing expectations.
- Lowers the technical barrier to motion adjustment in standard character workflows.
Summary
This SIGGRAPH 2024 paper introduces a system for iterative natural language editing of character animation. The approach uses kinematic motion operators that are explicitly aligned with the vocabulary and expectations of practising animators, allowing users to refine motion through successive natural language instructions rather than direct keyframe manipulation. By lowering the technical barrier to motion adjustment, the system points toward a workflow model that animation students need to understand as language-driven motion editing enters professional pipelines.
Related items
- A deep learning framework for character motion synthesis and editing (SIGGRAPH 2016 / SIGGRAPH 2026 Test-of-Time award)
- ToonCrafter: Generative Cartoon Interpolation
Source
Source: ACM SIGGRAPH 2024 ↗ (Research)
Cite this item
ACM SIGGRAPH 2024 (2024). ‘Iterative Motion Editing with Natural Language’, ACM SIGGRAPH 2024. Available at: https://dl.acm.org/doi/10.1145/3641519.3657447
Your reference manager can also read this page directly: with the Zotero (or Mendeley) browser connector installed, save it straight to your library. Whole-collection exports: RIS, BibTeX, CSL-JSON.