7 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…
DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior
Mingrui Li, Shuhong Liu, Tianchen Deng +1
Gaussian SLAM systems excel in real-time rendering and fine-grained reconstruction compared to NeRF-based systems. However, their reliance on extensive keyframes is impractical for…
STG-Avatar: Animatable Human Avatars via Spacetime Gaussian
Guangan Jiang, Tianzi Zhang, Dong Li +4
Realistic animatable human avatars from monocular videos are crucial for advancing human-robot interaction and enhancing immersive virtual experiences. While recent research on 3DG…
Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments
Mingrui Li, Yiming Zhou, Hongxing Zhou +4
Current Simultaneous Localization and Mapping (SLAM) methods based on Neural Radiance Fields (NeRF) or 3D Gaussian Splatting excel in reconstructing static 3D scenes but struggle w…
NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap
Jingwei Huang, Mingrui Li, Lei Sun +3
SLAM systems based on Gaussian Splatting have garnered attention due to their capabilities for rapid real-time rendering and high-fidelity mapping. However, current Gaussian Splatt…
GARAD-SLAM: 3D GAussian splatting for Real-time Anti Dynamic SLAM
Mingrui Li, Weijian Chen, Na Cheng +3
The 3D Gaussian Splatting (3DGS)-based SLAM system has garnered widespread attention due to its excellent performance in real-time high-fidelity rendering. However, in real-world e…