Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation.
Zibo ZhaoWen LiuXin ChenXianfang ZengRui WangPei ChengBin FuTao ChenGang YuShenghua GaoPublished in: CoRR (2023)
Keyphrases
- single image
- image representation
- object shape
- geometric shapes
- surface shape
- input image
- primal sketch
- image measurements
- image content
- image structure
- image classification
- image segmentation
- deformable template
- shape estimation
- spatial layout
- object shapes
- multiscale
- edge detection
- image features
- high resolution
- feature points
- spatial arrangement
- vector field
- energy functional
- invariant features
- image retrieval
- shape recovery
- segmentation method
- shape reconstruction
- textual descriptions
- chain code
- relative position
- web images
- d objects
- spatial relations
- lighting conditions
- invariant descriptors
- hand drawn
- spatial configuration
- shape matching
- global shape
- fourier descriptors
- bounding box
- object boundaries
- image regions
- multi view
- scale space
- image sequences
- three dimensional