2024/05/24 by You Meng, You, Meng, Zhiyu Zhu +5 · 27 citations
Computer Science · #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Video Coding and Compression Technologies
paper · pdf · doi:10.48550/arxiv.2405.15364
openalex publication_date 2024/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates without the need for training. NVS-Solver adaptively modulates the diffusion sampling process with the given views to enable the creation of remarkable visual experiences from single or multiple views of static scenes or monocular videos of dynamic scenes. Specifically, built upon our theoretical modeling, we iteratively modulate the score function with the given scene priors represented with warped input views to control the video diffusion process. Moreover, by theoretically exploring the boundary of the estimation error, we achieve the modulation in an adaptive fashion according to the view pose and the number of diffusion steps. Extensive evaluations on both static and dynamic scenes substantiate the significant superiority of our NVS-Solver over state-of-the-art methods both quantitatively and qualitatively. Source code in \hrefhttps://github.com/ZHU-Zhiyu/NVSSolverhttps://github.com/ZHU-Zhiyu/NVS_Solver.