D^2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video.
Tianhao WuFangcheng ZhongAndrea TagliasacchiForrester ColeCengiz ÖztireliPublished in: NeurIPS (2022)
Keyphrases
- multimedia objects
- image sequences
- video sequences
- video images
- dynamic environments
- video data
- multimedia
- dynamic textures
- moving objects
- d objects
- visual data
- video content
- video retrieval
- object segmentation
- dynamic scenes
- dynamic constraints
- stationary camera
- data objects
- multimedia data
- space time
- pose estimation
- object classes
- video analysis
- moving camera
- video objects
- video segments
- video frames
- object detection and tracking
- optical flow
- layered representation