DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting

TL;DR

DBMovi-GS is a novel method that synthesizes dynamic views from blurry monocular videos by generating dense 3D Gaussians, effectively restoring sharpness and scene geometry despite motion blur and scene dynamics.

Contribution

It introduces a motion-aware approach using sparse-controlled Gaussian splatting to handle dynamic scenes and blurry inputs, improving robustness and visual fidelity in novel view synthesis.

Findings

Achieves state-of-the-art results on blurry monocular video datasets.

Restores sharpness and detailed 3D geometry from blurry inputs.

Demonstrates robustness in dynamic scene view synthesis.

Abstract

Novel view synthesis is a task of generating scenes from unseen perspectives; however, synthesizing dynamic scenes from blurry monocular videos remains an unresolved challenge that has yet to be effectively addressed. Existing novel view synthesis methods are often constrained by their reliance on high-resolution images or strong assumptions about static geometry and rigid scene priors. Consequently, their approaches lack robustness in real-world environments with dynamic object and camera motion, leading to instability and degraded visual fidelity. To address this, we propose Motion-aware Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting (DBMovi-GS), a method designed for dynamic view synthesis from blurry monocular videos. Our model generates dense 3D Gaussians, restoring sharpness from blurry videos and reconstructing detailed 3D geometry of the scene affected by dynamic motion variations. Our model achieves robust performance in novel view synthesis under dynamic blurry scenes and sets a new benchmark in realistic novel view synthesis for blurry monocular video inputs.