BRUM improves sparse-view 3D vehicle reconstruction by synthesizing extra training views from depth and poses, using DUSt3R for real cameras, and weighting the photometric loss by pixel reliability.
Fewviewgs: Gaussian splatting with few view matching and multi-stage training,
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
background 1representative citing papers
citing papers explorer
-
BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images
BRUM improves sparse-view 3D vehicle reconstruction by synthesizing extra training views from depth and poses, using DUSt3R for real cameras, and weighting the photometric loss by pixel reliability.