.png){kind=icon}
Return
Hierarchical Bayesian Guided Spatial-, Angular- and Temporal-Consistent View Synthesis
.png){kind=icon}
PRE
AI
DOI：10.1109/TVCG.2025.3631702.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Neural Radiance Fields (NeRF) have gained significant attention due to their precise reconstruction and rapid inference capabilities, making them highly promising for applications in virtual reality and gaming. However, extending NeRF’s capabilities to dynamic scenes remains underexplored, particularly in ensuring consistent and coherent reconstructions across space, time, and viewing angles. To address this challenge, we propose Scale-NeRF, a novel approach that organizes the training of dynamic NeRFs as a progressive, scale-based refinement process, grounded in hierarchical Bayesian theory. Scale-NeRF begins by reconstructing the radiance fields using coarse, large-scale frames and iteratively refines them with progressively smaller-scale frames. This hierarchical strategy, combined with a corresponding sampling approach and a newly introduced structural loss, ensures consistency and integrity throughout the reconstruction process. Experiments on public datasets validate the superiority of Scale-NeRF over traditional methods, especially in terms of the proposed metrics evaluating spatial, angular, and temporal consistency. Furthermore, Scale-NeRF demonstrates excellent dynamic reconstruction capabilities with real-time rendering, offering a significant advancement for applications demanding both high fidelity and real-time performance.
Keywords:
Dynamic NeRF
inconsistent reconstruction
hierarchical bayesian theory
structural loss
consistent metrics
Journal
IF:
6.5
Papers:
353
Citations:
2.2W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
View more