DL-SLAM uses dual-level (pixel and object) dynamic probabilities from semantic-geometric fusion to produce artifact-free static maps and up to 13% better tracking accuracy in dynamic scenes.
Semgauss-slam: Dense semantic gaussian splatting slam,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
DSP-SLAM++ adds asynchronous mapping and fisheye-LiDAR fusion to DSP-SLAM, claiming up to 70% lower object processing latency and real-time performance on 25 Hz multi-class datasets while producing geometrically complete object models.
citing papers explorer
-
DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability
DL-SLAM uses dual-level (pixel and object) dynamic probabilities from semantic-geometric fusion to produce artifact-free static maps and up to 13% better tracking accuracy in dynamic scenes.
-
DSP-SLAM++: A Unified Framework for Multi-Class, High-Fidelity Object SLAM in the Wild
DSP-SLAM++ adds asynchronous mapping and fisheye-LiDAR fusion to DSP-SLAM, claiming up to 70% lower object processing latency and real-time performance on 25 Hz multi-class datasets while producing geometrically complete object models.