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.
Video-based reconstruction of 3d people models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.