Flash-Mono: Feed-Forward Accelerated Gaussian Splatting Monocular SLAM

TL;DR

Flash-Mono introduces a feed-forward Gaussian Splatting SLAM system that significantly improves speed and accuracy by predicting Gaussian attributes directly from multi-frame context, bypassing traditional optimization.

Contribution

The paper proposes a novel feed-forward architecture with a recurrent frontend for monocular SLAM, enabling 10x faster processing and improved geometric fidelity compared to prior optimization-based methods.

Findings

Achieves 10x speedup over traditional GS-SLAM methods.

Maintains high-quality rendering and mapping accuracy.

Enables efficient loop closure using hidden states as submap descriptors.

Abstract

Monocular 3D Gaussian Splatting SLAM suffers from critical limitations in time efficiency, geometric accuracy, and multi-view consistency. These issues stem from the time-consuming $\textit{Train-from-Scratch}$ optimization and the lack of inter-frame scale consistency from single-frame geometry priors. We contend that a feed-forward paradigm, leveraging multi-frame context to predict Gaussian attributes directly, is crucial for addressing these challenges. We present Flash-Mono, a system composed of three core modules: a feed-forward prediction frontend, a 2D Gaussian Splatting mapping backend, and an efficient hidden-state-based loop closure module. We trained a recurrent feed-forward frontend model that progressively aggregates multi-frame visual features into a hidden state via cross attention and jointly predicts camera poses and per-pixel Gaussian properties. By directly predicting Gaussian attributes, our method bypasses the burdensome per-frame optimization required in optimization-based GS-SLAM, achieving a $\textbf{10x}$ speedup while ensuring high-quality rendering. The power of our recurrent architecture extends beyond efficient prediction. The hidden states act as compact submap descriptors, facilitating efficient loop closure and global $\mathrm{Sim}(3)$ optimization to mitigate the long-standing challenge of drift. For enhanced geometric fidelity, we replace conventional 3D Gaussian ellipsoids with 2D Gaussian surfels. Extensive experiments demonstrate that Flash-Mono achieves state-of-the-art performance in both tracking and mapping quality, highlighting its potential for embodied perception and real-time reconstruction applications. Project page: https://victkk.github.io/flash-mono.