EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection.
Tengteng HuangZhe LiuXiwu ChenXiang BaiPublished in: CoRR (2020)
Keyphrases
- d objects
- point features
- multiple views
- viewpoint
- image features
- multi view
- input image
- feature points
- single image
- reference images
- object recognition
- image segmentation
- pose estimation
- range data
- object detection
- high resolution
- position and orientation
- three dimensional
- partial occlusion
- lighting conditions
- shape descriptors
- camera parameters
- geometric constraints
- image matching
- structure from motion
- range images