BEA-GS achieves superior object boundary segmentation in 3D Gaussian Splatting by introducing two new losses that adjust geometry of visible and non-visible Gaussians based on semantics.
3d gaussian splat- ting as markov chain monte carlo.Advances in Neural Infor- mation Processing Systems, 37:80965–80986
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2roles
background 1polarities
background 1representative citing papers
A dynamic training framework for 3D Gaussian Splatting alternates incremental pruning and adaptive growing of primitives to maintain high rendering quality at up to 80% lower peak memory than standard 3DGS.
citing papers explorer
-
BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction
BEA-GS achieves superior object boundary segmentation in 3D Gaussian Splatting by introducing two new losses that adjust geometry of visible and non-visible Gaussians based on semantics.
-
Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training
A dynamic training framework for 3D Gaussian Splatting alternates incremental pruning and adaptive growing of primitives to maintain high rendering quality at up to 80% lower peak memory than standard 3DGS.