Kimodo: Scaling Controllable Human Motion Generation
research.nvidia.com · 834 words · saved by 1 readers
Kimodo is a kinematic motion diffusion model trained on large-scale optical mocap data for easily generating high-quality 3D human and robot motions.
Your browser does not support the video tag. High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or kinematic constraints on poses. However, the small scale of public mocap datasets has limited the motion quality, control accuracy, and generalization of these models. In this work, we introduce Kimodo, an expressive and controllable kinematic motion diffusion model trained on 700 hours of…
saved by
related reading
- GitHub - yangtiming/Fast-SAM-3D-Body: [ECCV 2026] Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recoverygithub.com
- BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusionarxiv.org
- OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelsarxiv.org
- A Generative Motion Rig for Artist-Driven Motion Authoring | Disney Research Studiosstudios.disneyresearch.com
- The First Fully General Computer Action Model | blogsi.inc
- A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
- Empathetic Motion Generation for Humanoid Educational Robots via Reasoning-Guided Vision--Language--Motion Diffusion Architecturearxiv.org
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robotsarxiv.org
- UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robotsarxiv.org
- Generative Image Dynamicsgenerative-dynamics.github.io
- Differentiable Robot Renderingdrrobot.cs.columbia.edu
- Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com