A neural surface representation with foreground and background modules performs self-supervised object segmentation from multi-view images, producing finer masks than NeRF-based counterparts.
Multi- view object segmentation in space and time,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representation
A neural surface representation with foreground and background modules performs self-supervised object segmentation from multi-view images, producing finer masks than NeRF-based counterparts.