Abstract:Motion in-betweening is one of the most artistically demanding and time consuming stages of 3D animation, where the expressivity and rhythm of motion are defined. The level of creative control it requires makes it a major production bottleneck, underscoring the need for intelligent tools that assist animators in this process. Although recent deep learning approaches have achieved strong results in motion synthesis and in-betweening, they assume data characteristics, motion styles, and problem formulations that diverge from professional animation workflows. To bridge this gap, we propose a method explicitly aligned with the constraints of motion in-betweening for keyframe-based animation in production environments. At its core, the Adaptive Interpolation-Synthesis (AIS) layer mirrors the animator's creative process by dynamically balancing learned interpolation and direct pose synthesis. In addition, a domain-based input keypose schedule reflects the distribution of production data, improving stylistic consistency and alignment between training and real-world usage. Our method achieves state-of-the-art performance on production data; when integrated into Autodesk Maya, it enables animators to complete in-betweening tasks with a 3.5x speedup.
| Comments: | Accepted to SIGGRAPH 2026 Conference Papers |
| Subjects: | Graphics (cs.GR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.02742 [cs.GR] |
| (or arXiv:2605.02742v1 [cs.GR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02742 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.1145/3799902.3811157
DOI(s) linking to related resources |
From: Anton Rael [view email]
[v1]
Mon, 4 May 2026 15:41:42 UTC (15,109 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。