Constructs continuous sign conversation data from isolated signs using retrieval and diffusion models to train a direct sign-to-sign conversational AI.
Expressive body capture: 3d hands, face, and body from a single image
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
SMPL-GPTexture uses text-to-image generation to produce dual-view human images, aligns them to SMPL meshes via 2D-to-3D recovery, projects colors to UV space, and applies diffusion inpainting to create full high-resolution textures aligned to user prompts.
citing papers explorer
-
Towards Continuous Sign Language Conversation from Isolated Signs
Constructs continuous sign conversation data from isolated signs using retrieval and diffusion models to train a direct sign-to-sign conversational AI.
-
SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Models
SMPL-GPTexture uses text-to-image generation to produce dual-view human images, aligns them to SMPL meshes via 2D-to-3D recovery, projects colors to UV space, and applies diffusion inpainting to create full high-resolution textures aligned to user prompts.
- EgoExo-WM: Unlocking Exo Video for Ego World Models