Confidence-weighted multi-view geometric priors from VGGT improve 3D Gaussian splatting reconstruction on specular objects, cutting normal MAE on Shiny Blender from 3.23 to 1.23 degrees.
In: International Confer- ence on Learning Representations
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
-
Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction
Confidence-weighted multi-view geometric priors from VGGT improve 3D Gaussian splatting reconstruction on specular objects, cutting normal MAE on Shiny Blender from 3.23 to 1.23 degrees.