MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting Through Multi-View Fusion of LiDAR Data.
Ankit LaddhaShivam GautamStefan PalomboShreyash PandeyCarlos Vallespi-GonzalezPublished in: CVPR Workshops (2021)
Keyphrases
- end to end
- multi view
- lidar data
- object detection
- dynamic scenes
- multiple views
- motion estimation
- d objects
- three dimensional
- optical flow
- semi supervised
- urban environments
- depth map
- point cloud
- high resolution
- image sequences
- range images
- computer vision
- object segmentation
- object categories
- object recognition
- camera motion
- face detection
- moving objects
- multi sensor
- feature points
- viewpoint