MCDS-VSS: Moving Camera Dynamic Scene Video Semantic Segmentation by Filtering with Self-Supervised Geometry and Motion.
Angel Villar-CorralesMoritz AustermannSven BehnkePublished in: CoRR (2024)
Keyphrases
- moving camera
- dynamic scenes
- space time
- video sequences
- video camera
- multi view
- moving objects
- background subtraction
- motion segmentation
- foreground objects
- superpixels
- three dimensional
- camera motion
- multiple views
- frame rate
- image sequences
- motion parameters
- spatio temporal
- object recognition
- dynamic textures
- video frames
- video data
- motion estimation
- pairwise