WaterSplat-SLAM achieves robust camera tracking and high-fidelity rendering in underwater environments by coupling semantic medium filtering into two-view reconstruction and using an online medium-aware Gaussian map.
Mast3r-slam: Real- time dense slam with 3d reconstruction priors
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
VGGT-SLAM aligns VGGT submaps via SL(4) manifold optimization of 15-DoF homographies to enable consistent dense RGB SLAM on long uncalibrated monocular videos.
MoPe propagates historical dynamic posteriors via SE(3) warping and bounded Bayesian fusion to maintain persistent motion state in monocular Gaussian SLAM.
OVGGT achieves constant O(1) memory and compute for streaming 3D geometry reconstruction by using FFN-residual-based KV cache compression and dynamic anchor protection, matching state-of-the-art accuracy on long sequences.
R³ uses relative regression with confidence-weighted constraints from an MLP to support long-context offline and streaming 3D reconstruction without global coordinate assumptions.
Unreal Robotics Lab integrates Unreal Engine rendering with MuJoCo physics to enable high-fidelity simulation for robotics perception, control, and benchmarking under diverse conditions.
citing papers explorer
-
WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment
WaterSplat-SLAM achieves robust camera tracking and high-fidelity rendering in underwater environments by coupling semantic medium filtering into two-view reconstruction and using an online medium-aware Gaussian map.
-
VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
VGGT-SLAM aligns VGGT submaps via SL(4) manifold optimization of 15-DoF homographies to enable consistent dense RGB SLAM on long uncalibrated monocular videos.
-
MoPe: Motion Permanence for Robust Monocular Gaussian Mapping in Dynamic Environments
MoPe propagates historical dynamic posteriors via SE(3) warping and bounded Bayesian fusion to maintain persistent motion state in monocular Gaussian SLAM.
-
$R^3$: 3D Reconstruction via Relative Regression
R³ uses relative regression with confidence-weighted constraints from an MLP to support long-context offline and streaming 3D reconstruction without global coordinate assumptions.
-
Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering
Unreal Robotics Lab integrates Unreal Engine rendering with MuJoCo physics to enable high-fidelity simulation for robotics perception, control, and benchmarking under diverse conditions.