PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection.
Anthony ChenKevin ZhangRenrui ZhangZihan WangYuheng LuYandong GuoShanghang ZhangPublished in: CoRR (2023)
Keyphrases
- d objects
- point cloud
- real world objects
- image contours
- physically plausible
- cad model
- multi views
- image data
- viewpoint
- object recognition
- image features
- input image
- object matching
- pose estimation
- d mesh
- shape descriptors
- computer graphics
- multi view
- surface properties
- multiple views
- single image
- point sets
- laser scanner
- range data
- image matching
- structure from motion
- object classes
- hough transform
- similarity measure
- control points
- visual hull
- image sequences