A variance-aware conditional MLP operating on 3D Gaussians corrects semantic errors from multi-view inconsistent 2D features to produce more accurate and robust 3D semantic Gaussian Splatting.
Egosplat: Open-vocabulary egocentric scene understanding with language embed- ded 3d gaussian splatting
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
DF3DV-1K supplies 1,048 real scenes with clean/cluttered image pairs and a 41-scene hard subset to benchmark and improve distractor-free radiance-field methods.
citing papers explorer
-
NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting
A variance-aware conditional MLP operating on 3D Gaussians corrects semantic errors from multi-view inconsistent 2D features to produce more accurate and robust 3D semantic Gaussian Splatting.
-
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
DF3DV-1K supplies 1,048 real scenes with clean/cluttered image pairs and a 41-scene hard subset to benchmark and improve distractor-free radiance-field methods.