Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video.
Edgar TretschkAyush TewariVladislav GolyanikMichael ZollhöferChristoph LassnerChristian TheobaltPublished in: ICCV (2021)
Keyphrases
- dynamic scenes
- video sequences
- space time
- combining information from multiple
- multi view
- temporal coherence
- video camera
- camera setups
- temporally coherent
- image sequences
- image frames
- moving camera
- motion segmentation
- motion estimation
- high dynamic range
- moving objects
- background subtraction
- three dimensional
- frame rate
- motion blur
- multiple views
- video frames
- exposure fusion
- video data
- high resolution
- dynamic range
- foreground objects
- computer vision
- light field
- optical flow
- active learning
- pairwise