NeuralDiff: Segmenting 3D objects that move in egocentric videos.
Vadim TschernezkiDiane LarlusAndrea VedaldiPublished in: CoRR (2021)
Keyphrases
- d objects
- multi view
- object recognition
- viewpoint
- three dimensional
- pose estimation
- video summarization
- shape descriptors
- video sequences
- activity recognition
- video frames
- range data
- human activities
- invariant recognition
- image segmentation
- object features
- cad models
- dynamic scenes
- d mesh
- polyhedral objects
- geometric models
- long video sequences
- video data
- object views
- visual features