A lightweight neural model fuses 3D point cloud reconstructions with view-aligned 2D features via a graph decoder to regress volume, surface area, and uncertainties from multi-view images without iterative optimization.
arXiv preprint arXiv:2107.02259 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lightweight Neural Framework for Robust 3D Volume and Surface Estimation from Multi-View Images
A lightweight neural model fuses 3D point cloud reconstructions with view-aligned 2D features via a graph decoder to regress volume, surface area, and uncertainties from multi-view images without iterative optimization.