Animatica Marionette
Summary
Animatica Marionette 是一个面向 Blender 的神经控制绑定工具,拖动手、脚或臀部即可带动全身姿势,可在本机约 15 毫秒内生成一个姿势,并直接兼容 Mixamo、Unreal 等现成人形绑定。
View Cached Full Text
Cached at: 10/21/26, 08:19 AM
Similar Articles
@RemiFabreRobot: Today we're releasing Marionette: create robot motion with your hands (Reachy Mini). Browser-based, works on phone or c…
The article announces the release of Marionette, a browser-based tool that allows users to record and share robot motions for the Reachy Mini using their phones or computers.
@lxfater: Want to make a movable 3D avatar for yourself, but don't know Blender? You can check out this one. Nano made a toolkit …
Nano(@Dstudio_ai)开源了名为 Charakuru(きゃらくる)的工具包,可结合 Tripo 与 Codex 将一张全身立绘转成可动的 VRM 虚拟形象,并将零散的建模流程整合为本地应用加 7 个 Skills 的人机协作工作流。
InterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation
InterMimicGen 提出一个自我进化的运动模仿框架,通过数据飞轮将稀疏的人-物交互动作捕捉数据转化为持续扩展的、可执行的人形机器人全身 loco-manipulation 动作资源,并实现向真实机器人的迁移。
@FinanceYF5: This is insane. NVIDIA just released MotionBricks at SIGGRAPH 2026. This AI lets game characters and robots master over 350,000 motion skills. 15,000 FPS. 2ms latency. 1. Smart movement: characters can now switch movement styles instantly…
NVIDIA has released MotionBricks at SIGGRAPH 2026, an AI model that enables game characters and robots to master over 350,000 motion skills, reaching up to 15,000 FPS with just 2ms latency.
PAMI: Part Anchored Motion for Text to Human-Object Interaction Generation
PAMI 提出一种 Part-Anchored Motion 框架,通过身体部位锚点投票机制和粗到细的生成层级(PamiGen 与 PamiRefiner)实现文本条件下的全身人-物交互生成,在 InterAct 数据集上较此前 SOTA 提升 14.5% 的接触召回率。