4 papers
MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM
Fan Zhu, Ziyu Chen, Zhenjun Zhao +5
Real-time monocular Simultaneous Localization and Mapping (SLAM) fundamentally suffers from scale ambiguity and a lack of geometric self-correction. While 3D Gaussian Splatting (3D…
Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments
Xiangqi Meng, Pengxu Hou, Zhenjun Zhao +4
In addition to the core tasks of simultaneous localization and mapping (SLAM), active SLAM additionally in- volves generating robot actions that enable effective and efficient expl…
VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasets
Alejandro Fontan, Tobias Fischer, Javier Civera +1
Visual Simultaneous Localization and Mapping (VSLAM) research faces significant challenges due to fragmented toolchains, complex system configurations, and inconsistent evaluation…
Look Ma, No Ground Truth! Ground-Truth-Free Tuning of Structure from Motion and Visual SLAM
Alejandro Fontan, Javier Civera, Tobias Fischer +1
Evaluation is critical to both developing and tuning Structure from Motion (SfM) and Visual SLAM (VSLAM) systems, but is universally reliant on high-quality geometric ground truth…