Kimodo: Scaling Controllable Human Motion Generation

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

• John Zhang

related reading

• GitHub - AmmarkoV/SAM3DBody-cpp: Real-time 3D full-body reconstruction from a single camera, Multiperson BVH output, Pure C++ runtime, ONNX + ggml, 70-joint skeleton with hands.github.com
• A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusiondiffusion-policy.cs.columbia.edu
• Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
• BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusionarxiv.org
• [2207.13807] Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldsarxiv.org
• Humanoid Atlas | Humanoid Robot Supply Chain Map, OEM Database & Industry Analysishumanoids.fyi
• OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelsarxiv.org
• Causal Video Models Are Data-Efficient Robot Policy Learners | Rhoda AIrhoda.ai
• Generating Robot Hands from Human Demonstrationsarxiv.org
• Diffusion models from scratchchenyang.co
• GitHub - adam-maj/robotics: A deep dive on the history of robotics and the future of humanoidsgithub.com