Broadening View Synthesis of Dynamic Scenes from Constrained Monocular Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Le, Zhu, Shaotong, Luo, Yedi, Moezzi, Shayda, Ostadabbas, Sarah
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908714718461952
author Jiang, Le
Zhu, Shaotong
Luo, Yedi
Moezzi, Shayda
Ostadabbas, Sarah
author_facet Jiang, Le
Zhu, Shaotong
Luo, Yedi
Moezzi, Shayda
Ostadabbas, Sarah
contents In dynamic Neural Radiance Fields (NeRF) systems, state-of-the-art novel view synthesis methods often fail under significant viewpoint deviations, producing unstable and unrealistic renderings. To address this, we introduce Expanded Dynamic NeRF (ExpanDyNeRF), a monocular NeRF framework that leverages Gaussian splatting priors and a pseudo-ground-truth generation strategy to enable realistic synthesis under large-angle rotations. ExpanDyNeRF optimizes density and color features to improve scene reconstruction from challenging perspectives. We also present the Synthetic Dynamic Multiview (SynDM) dataset, the first synthetic multiview dataset for dynamic scenes with explicit side-view supervision-created using a custom GTA V-based rendering pipeline. Quantitative and qualitative results on SynDM and real-world datasets demonstrate that ExpanDyNeRF significantly outperforms existing dynamic NeRF methods in rendering fidelity under extreme viewpoint shifts. Further details are provided in the supplementary materials.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14406
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Broadening View Synthesis of Dynamic Scenes from Constrained Monocular Videos
Jiang, Le
Zhu, Shaotong
Luo, Yedi
Moezzi, Shayda
Ostadabbas, Sarah
Computer Vision and Pattern Recognition
In dynamic Neural Radiance Fields (NeRF) systems, state-of-the-art novel view synthesis methods often fail under significant viewpoint deviations, producing unstable and unrealistic renderings. To address this, we introduce Expanded Dynamic NeRF (ExpanDyNeRF), a monocular NeRF framework that leverages Gaussian splatting priors and a pseudo-ground-truth generation strategy to enable realistic synthesis under large-angle rotations. ExpanDyNeRF optimizes density and color features to improve scene reconstruction from challenging perspectives. We also present the Synthetic Dynamic Multiview (SynDM) dataset, the first synthetic multiview dataset for dynamic scenes with explicit side-view supervision-created using a custom GTA V-based rendering pipeline. Quantitative and qualitative results on SynDM and real-world datasets demonstrate that ExpanDyNeRF significantly outperforms existing dynamic NeRF methods in rendering fidelity under extreme viewpoint shifts. Further details are provided in the supplementary materials.
title Broadening View Synthesis of Dynamic Scenes from Constrained Monocular Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.14406