Sign in
Temporally Consistent Semantic Segmentation using Spatially Aware Multi-view Semantic Fusion for Indoor RGB-D videos.
Fengyuan Sun
Sezer Karaoglu
Theo Gevers
Published in:
ICCV (Workshops) (2023)
Keyphrases
</>
multi view
depth map
multiple views
superpixels
depth information
d objects
three dimensional
video sequences
semi supervised
key frames
stereo matching
video frames
high quality
d scene
video data
graphical models
ground truth
viewpoint
depth estimation