Anatomical Motion Diffusion model generates realistic human motion from text

Researchers have developed Anatomical Motion Diffusion (AMD), a novel model designed to generate realistic human motion sequences from text descriptions. AMD utilizes a Large Language Model (LLM) to parse complex text inputs into interpretable anatomical scripts, which then guide the diffusion process. This approach allows AMD to effectively handle intricate or lengthy motion descriptions where previous methods have struggled. Experiments on datasets like CLCD1 and CLCD2 show AMD significantly outperforms existing state-of-the-art models in synthesizing diverse and semantically accurate motions. AI

IMPACT This model could advance realistic human motion synthesis for applications in animation, gaming, and robotics.

RANK_REASON The cluster contains an academic paper detailing a new model and its experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• AMD
• Anatomical Motion Diffusion
• arXiv
• Beibei Jing
• CLCD1
• cleidocranial dysplasia 2
• large language model

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →