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