A new RGBD SLAM representation ties Gaussian positions to depth pixels, leaving only color, radius, and opacity learnable, enabling local-only optimization and higher rendering quality on several benchmarks.
∗ indicates methods relying on pre-trained data-driven priors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians
A new RGBD SLAM representation ties Gaussian positions to depth pixels, leaving only color, radius, and opacity learnable, enabling local-only optimization and higher rendering quality on several benchmarks.