2025/06/26 by Yeon-Ji Song, Jaein Kim, Song, Yeon-Ji +5
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Benchmark (surveying) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gaussian #Image and Video Quality Assessment #Monocular #Robustness (evolution) #View synthesis #Visual hull
paper · pdf · doi:10.48550/arxiv.2506.20998
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/06/26 · openalex created_date 2025/10/15 · openalex updated_date 2026/08/05
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.