ExpanDyNeRF: Expanding the Viewpoint of Dynamic Scenes beyond Constrained Camera Motions

Le Jiang, Shaotong Zhu, Yedi Luo, Sarah Ostadabbas, Shayda Moezzi

Keywords: NeRF, Dynamic NeRF, Generative Models, Super Resolution

TL;DR: ExpanDyNeRF resolves ghosting and blurring in Dynamic NeRF rendering after camera rotations by generating pseudo ground truth for side views, and we are the first to use GTA to create a dataset for quantitative analysis on novel views.

Abstract: In the domain of dynamic Neural Radiance Fields (NeRF) for novel view synthesis, current state-of-the-art (SOTA) techniques struggle when the camera's pose deviates significantly from the primary viewpoint, resulting in unstable and unrealistic outcomes. This paper introduces Expanded Dynamic NeRF (ExpanDyNeRF), a monocular NeRF method that integrates a Gaussian splatting prior to tackle novel view synthesis with large-angle rotations. ExpanDyNeRF employs a pseudo ground truth technique to optimize density and color features, which enables the generation of realistic scene reconstructions from challenging viewpoints. Additionally, we present the Synthetic Dynamic Multiview (SynDM) dataset, the first GTA V-based dynamic multiview dataset designed specifically for evaluating robust dynamic reconstruction from significantly shifted views. We evaluate our method quantitatively and qualitatively on both the SynDM dataset and the widely recognized NVIDIA dataset, comparing it against other SOTA methods for dynamic scene reconstruction. Our evaluation results demonstrate that our method achieves superior performance.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3262