UDGS-SLAM : UniDepth Assisted Gaussian Splatting for Monocular SLAM

TL;DR

UDGS-SLAM introduces a monocular SLAM method that integrates UniDepth-based depth estimation with Gaussian splatting, achieving high-fidelity rendering and accurate camera tracking without RGB-D sensors.

Contribution

It presents a novel monocular SLAM framework combining UniDepth and Gaussian splatting, eliminating the need for RGB-D sensors and enhancing scene reconstruction accuracy.

Findings

Achieves high-fidelity rendered images.

Demonstrates low ATERMSE in camera trajectory estimation.

Outperforms baseline methods on TUM RGB-D dataset.

Abstract

Recent advancements in monocular neural depth estimation, particularly those achieved by the UniDepth network, have prompted the investigation of integrating UniDepth within a Gaussian splatting framework for monocular SLAM. This study presents UDGS-SLAM, a novel approach that eliminates the necessity of RGB-D sensors for depth estimation within Gaussian splatting framework. UDGS-SLAM employs statistical filtering to ensure local consistency of the estimated depth and jointly optimizes camera trajectory and Gaussian scene representation parameters. The proposed method achieves high-fidelity rendered images and low ATERMSE of the camera trajectory. The performance of UDGS-SLAM is rigorously evaluated using the TUM RGB-D dataset and benchmarked against several baseline methods, demonstrating superior performance across various scenarios. Additionally, an ablation study is conducted to validate design choices and investigate the impact of different network backbone encoders on system performance.