SpatialDETR: Robust Scalable Transformer-Based 3D Object Detection From Multi-view Camera Images With Global Cross-Sensor Attention.
Simon DollRichard SchulzLukas SchneiderViviane BenzinMarkus EnzweilerHendrik P. A. LenschPublished in: ECCV (39) (2022)
Keyphrases
- multi view
- d objects
- multiple views
- single view
- viewpoint
- depth map
- object recognition
- three dimensional
- dynamic scenes
- camera calibration
- multiple cameras
- pose estimation
- range data
- multi views
- range images
- bundle adjustment
- surface patches
- partial occlusion
- photometric stereo
- multiple images
- object detection
- camera parameters
- object classes
- point correspondences
- fundamental matrix
- machine learning
- computer vision