MonoGS++: Fast and Accurate Monocular RGB Gaussian SLAM

📅 2025-04-03
📈 Citations: 2
Influential: 0
📄 PDF
🤖 AI Summary
To address the lack of depth priors, poor reconstruction in textureless regions, and Gaussian redundancy in monocular RGB SLAM, this paper proposes a real-time, high-accuracy SLAM framework that requires no depth sensor. Methodologically, it tightly integrates online visual odometry (VO) with 3D Gaussian Splatting, incorporating a dynamic Gaussian insertion mechanism, a sharpness-driven adaptive densification module, and plane-based geometric regularization—collectively enhancing dense reconstruction quality and geometric consistency under sparse feature constraints. Evaluated on Replica and TUM-RGBD datasets, the method achieves state-of-the-art tracking accuracy and attains millisecond-level real-time performance, with inference speed 5.57× faster than the baseline. Key contributions include: (i) the first dynamic Gaussian management strategy tailored for monocular SLAM, and (ii) a multi-level geometric regularization paradigm, effectively mitigating drift in textureless scenes and Gaussian over-saturation.

Technology Category

Application Category

📝 Abstract
We present MonoGS++, a novel fast and accurate Simultaneous Localization and Mapping (SLAM) method that leverages 3D Gaussian representations and operates solely on RGB inputs. While previous 3D Gaussian Splatting (GS)-based methods largely depended on depth sensors, our approach reduces the hardware dependency and only requires RGB input, leveraging online visual odometry (VO) to generate sparse point clouds in real-time. To reduce redundancy and enhance the quality of 3D scene reconstruction, we implemented a series of methodological enhancements in 3D Gaussian mapping. Firstly, we introduced dynamic 3D Gaussian insertion to avoid adding redundant Gaussians in previously well-reconstructed areas. Secondly, we introduced clarity-enhancing Gaussian densification module and planar regularization to handle texture-less areas and flat surfaces better. We achieved precise camera tracking results both on the synthetic Replica and real-world TUM-RGBD datasets, comparable to those of the state-of-the-art. Additionally, our method realized a significant 5.57x improvement in frames per second (fps) over the previous state-of-the-art, MonoGS.
Problem

Research questions and friction points this paper is trying to address.

Develops fast RGB-only SLAM using 3D Gaussians
Reduces hardware dependency by eliminating depth sensors
Improves reconstruction quality via dynamic Gaussian management
Innovation

Methods, ideas, or system contributions that make the work stand out.

Uses 3D Gaussian representations with RGB-only input
Implements dynamic Gaussian insertion to reduce redundancy
Enhances clarity with densification and planar regularization
💼 Related Jobs
No related jobs found.
R
Ren-Wu Li
Advanced Micro Devices, Inc.
W
Wenjing Ke
Advanced Micro Devices, Inc.
D
Dong Li
Advanced Micro Devices, Inc.
L
Lu Tian
Advanced Micro Devices, Inc.
E
E. Barsoum
Advanced Micro Devices, Inc.