NeuralDiff: Segmenting 3D objects that move in egocentric videos.
Vadim TschernezkiDiane LarlusAndrea VedaldiPublished in: 3DV (2021)
Keyphrases
- d objects
- viewpoint
- multi view
- object recognition
- three dimensional
- video sequences
- shape descriptors
- pose estimation
- activity recognition
- video frames
- video summarization
- human activities
- range data
- cad models
- line drawings
- image contours
- dynamic scenes
- object classes
- video data
- object representation
- texture mapping
- invariant recognition
- image segmentation
- object features
- partial matching
- polyhedral objects
- virtual environment
- recognizing objects
- natural images
- curved objects
- pose normalization
- recognition and pose estimation