Deblur Gaussian Splatting SLAM

2025-03-16

AI Summary

This work addresses the degradation of RGB SLAM performance under motion blur by proposing the first end-to-end Gaussian Splatting SLAM framework that jointly performs deblurring and sub-frame trajectory estimation. Methodologically: (1) it couples a physics-based motion blur model with Gaussian splatting representation to establish a differentiable blurred image synthesis and virtual sub-frame averaging rendering mechanism; (2) it introduces monocular depth-guided Gaussian deformation to improve geometric reconstruction accuracy; and (3) it integrates online loop closure and global bundle adjustment for robust, real-time dense reconstruction. The key innovation lies in unifying explicit 3D representation, sub-frame camera modeling, and physics-driven deblurring within a single differentiable optimization framework. Evaluated on both synthetic and real-world motion-blurred datasets, the method achieves state-of-the-art performance—significantly enhancing map sharpness and enabling sub-frame-level trajectory accuracy—while supporting real-time, high-fidelity SLAM and deblurred reconstruction.

Technology Category

• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We present Deblur-SLAM, a robust RGB SLAM pipeline designed to recover sharp reconstructions from motion-blurred inputs. The proposed method bridges the strengths of both frame-to-frame and frame-to-model approaches to model sub-frame camera trajectories that lead to high-fidelity reconstructions in motion-blurred settings. Moreover, our pipeline incorporates techniques such as online loop closure and global bundle adjustment to achieve a dense and precise global trajectory. We model the physical image formation process of motion-blurred images and minimize the error between the observed blurry images and rendered blurry images obtained by averaging sharp virtual sub-frame images. Additionally, by utilizing a monocular depth estimator alongside the online deformation of Gaussians, we ensure precise mapping and enhanced image deblurring. The proposed SLAM pipeline integrates all these components to improve the results. We achieve state-of-the-art results for sharp map estimation and sub-frame trajectory recovery both on synthetic and real-world blurry input data.

Problem

• Recover sharp reconstructions from motion-blurred inputs
• Model sub-frame camera trajectories for high-fidelity reconstructions
• Integrate online loop closure and global bundle adjustment

Innovation

• Combines frame-to-frame and frame-to-model approaches
• Models physical image formation for motion blur
• Integrates monocular depth with Gaussian deformation