LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation.
Keunhong ParkArsalan MousavianYu XiangDieter FoxPublished in: CVPR (2020)
Keyphrases
- end to end
- pose estimation
- d objects
- shape from silhouettes
- object recognition and pose estimation
- visual hull
- object pose
- position and orientation
- pose recovery
- invariant recognition
- pose parameters
- human pose
- human body
- camera pose estimation
- human pose estimation
- computer vision
- head pose estimation
- implicit polynomial
- congestion control
- complex objects
- multi view
- three dimensional
- feature points
- viewpoint
- discrete space
- computer graphics
- object recognition
- pictorial structure
- multiple cameras
- monocular images
- depth images
- implicit surfaces
- training set
- high resolution
- real time
- body parts
- multiple views