Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss.
Eskil JörgensenChristopher ZachFredrik KahlPublished in: CoRR (2019)
Keyphrases
- end to end
- d objects
- pose estimation
- minimum bounding
- viewpoint
- text localization and recognition
- object recognition
- multi view
- multiple views
- shape descriptors
- three dimensional
- range data
- line drawings
- admission control
- congestion control
- cad models
- object detection
- geometric models
- image contours
- object classes
- application layer
- image sequences
- pose normalization
- training set
- physically plausible