Zero-1-to-3: Zero-shot One Image to 3D Object.
Ruoshi LiuRundi WuBasile Van HoorickPavel TokmakovSergey ZakharovCarl VondrickPublished in: CoRR (2023)
Keyphrases
- d objects
- physically plausible
- image contours
- curved objects
- input image
- image data
- image features
- invariant recognition
- image content
- multi views
- d mesh
- single image
- image segmentation
- object parts
- object features
- object recognition
- object matching
- real world objects
- surface properties
- three dimensional
- shape descriptors
- multi view
- image retrieval
- viewpoint
- image synthesis
- surface patches
- pose estimation
- multiple views
- range data
- recognition and pose estimation
- line drawings
- geometric invariants
- cad models
- topological information
- energy function
- segmentation method
- three dimensional objects
- computer vision algorithms
- salient features
- object classes
- surface points
- hough transform
- image matching
- object representation
- feature points
- test images