MU-GeNeRF combines source-view and target-view uncertainties via a heteroscedastic loss to enable distractor-aware generalizable NeRF reconstruction that matches scene-specific methods.
Neural radiance field-based visual rendering: A comprehensive review
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A guided mobile capture method for object-centered 3D Gaussian Splatting uses sensor-based pose alignment and area-weighted spherical coverage to achieve superior reconstruction quality with fewer images than free capture or RealityScan.
citing papers explorer
-
MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
MU-GeNeRF combines source-view and target-view uncertainties via a heteroscedastic loss to enable distractor-aware generalizable NeRF reconstruction that matches scene-specific methods.
-
An Object-Centered Data Acquisition Method for 3D Gaussian Splatting using Mobile Phones
A guided mobile capture method for object-centered 3D Gaussian Splatting uses sensor-based pose alignment and area-weighted spherical coverage to achieve superior reconstruction quality with fewer images than free capture or RealityScan.