Emdm: Efficient motion diffusion model for fast, high-quality motion generation
We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human
motion generation. Current state-of-theart generative diffusion models have produced …
motion generation. Current state-of-theart generative diffusion models have produced …
DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image
Reconstructing 3D hand-face interactions with deformations from a single image is a
challenging yet crucial task with broad applications in AR, VR, and gaming. The challenges …
challenging yet crucial task with broad applications in AR, VR, and gaming. The challenges …
InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction
Text-conditioned human motion generation has experienced significant advancements with
diffusion models trained on extensive motion capture data and corresponding textual …
diffusion models trained on extensive motion capture data and corresponding textual …
COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models
We propose a novel framework COLLAGE for generating collaborative agent-object-agent
interactions by leveraging large language models (LLMs) and hierarchical motion-specific …
interactions by leveraging large language models (LLMs) and hierarchical motion-specific …
[PDF][PDF] Plan, Posture and Go: Towards Open-vocabulary Text-to-Motion Generation
Conventional text-to-motion generation methods are usually trained on limited text-motion
pairs, making them hard to generalize to open-vocabulary scenarios. Some works use the …
pairs, making them hard to generalize to open-vocabulary scenarios. Some works use the …