Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Point Clouds.
Michael DanielczukMatthew MatlSaurabh GuptaAndrew LiAndrew LeeJeffrey MahlerKen GoldbergPublished in: CoRR (2018)
Keyphrases
- d objects
- point cloud
- depth images
- pose estimation
- multi view
- surface reconstruction
- cad model
- viewpoint
- object recognition
- three dimensional
- real objects
- multiple views
- structure from motion
- point sets
- planar surfaces
- range data
- color information
- shape descriptors
- depth map
- image segmentation
- image based rendering
- stereo camera
- training set
- photorealistic
- real scenes
- depth information
- low resolution