Skip to main content
GameDev.net gamedev.net

Motion Synthesis News

The latest Motion Synthesis coverage curated for game developers.

Generalized Audio-Driven Synthesis of Precise Drummer Motion

A new diffusion-based system can synthesize drummer motion from audio with centimeter-level stick accuracy while keeping the body movement natural. It targets the hard part of music-driven animation: fast, high-precision …

Research arXiv cs.GR · 4 weeks ago
MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance

For animation teams, the useful bit is that MultiAct can steer pretrained text-to-motion models toward composite prompts without retraining them. It tackles the common failure mode where a model latches …

Research arXiv cs.GR · 3 months, 2 weeks ago
SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control

SCRIPT pushes language-driven humanoid control toward more stable, physically plausible motion. The system combines a diffusion policy with multi-stage training, then adds reinforcement learning to improve instruction following and motion …

Research arXiv cs.GR · 3 months, 3 weeks ago
Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations

2D video motion is being used as training data for 3D human motion generation, which could widen the motion library available to games without relying so heavily on expensive mocap. …

Research arXiv cs.GR · 3 months, 4 weeks ago
AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro

A new motion-synthesis paper tackles sparse character control with a two-stage approach: first it conditions a frozen text-to-motion diffusion prior on a few anchors, then it refines the result by …

Research arXiv cs.GR · 4 months ago
FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesis

FatigueFusion introduces a novel deep-learning architecture that allows developers to synthesize fatigue-driven motion in 3D animations. This tool offers a significant advancement for graphics programmers and animators, enabling the creation …

Research arXiv cs.GR · 5 months ago
Fatigue-PINN: Physics-Informed Fatigue-Driven Motion Modulation and Synthesis

Fatigue-PINN introduces a novel approach to motion synthesis by integrating physics-informed neural networks to model human fatigue. This advancement allows for smoother animations and more realistic character movements, which is …

Research arXiv cs.GR · 5 months ago
Back to Basics: Motion Representation Matters for Human Motion Generation Using Diffusion Model

The study on motion representation in diffusion models reveals significant differences in performance across various configurations. This is crucial for developers focused on human motion generation, as it directly impacts …

Research arXiv cs.GR · 9 months, 1 week ago