A training-free graph-cut method selects 3D objects from Gaussian splatting scenes using sparse user scribbles, reaching 92.2 mIoU on NVOS with three interaction views.
Proceedings of the European conference on computer vision (ECCV) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization
A training-free graph-cut method selects 3D objects from Gaussian splatting scenes using sparse user scribbles, reaching 92.2 mIoU on NVOS with three interaction views.