Key points
- Holden, Saito and Komura's 2016 SIGGRAPH paper received the SIGGRAPH 2026 Test-of-Time award, recognising its lasting impact on neural character animation.
- The paper introduced a deep-learning framework for character motion synthesis and editing using convolutional autoencoders.
- Its approach underpins a decade of neural character-animation methods now standard in research and production pipelines.
Summary
Published at SIGGRAPH 2016 and awarded the SIGGRAPH 2026 Test-of-Time award, this paper by Holden, Saito and Komura established the deep-learning approach to character motion synthesis and editing that has shaped the field for a decade. Using convolutional autoencoders, it enabled natural, controllable character motion generation from data rather than hand-keyed animation. The Test-of-Time award marks it as a canonical reference for animation curricula covering the origins and development of neural character animation.
Related items
- Iterative Motion Editing with Natural Language
- AnimateDiff: Animate Your Personalized Text-to-Image Models without Specific Tuning
Source
Source: ACM Digital Library ↗ (Research)
Cite this item
Holden, D., Saito, J. & Komura, T. (2016). ‘A deep learning framework for character motion synthesis and editing (SIGGRAPH 2016 / SIGGRAPH 2026 Test-of-Time award)’, ACM Digital Library. Available at: https://dl.acm.org/doi/10.1145/2897824.2925975
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.