让单目动态场景在大角度视角下也能真实渲染
Broadening View Synthesis of Dynamic Scenes from Constrained Monocular Videos
- 用高斯点阵先验和伪真值生成提升视角泛化能力
- 在极端视角下渲染质量显著优于现有方法
- 适合做动态场景3D重建与视觉生成的研究者
在动态神经辐射场（NeRF）系统中，现有先进视图合成方法在大幅视角偏移下常失效，导致渲染不稳定且不真实。为此，本文提出扩展型动态NeRF（ExpanDyNeRF），一种基于单目视频的NeRF框架，利用高斯点阵先验和伪真值生成策略，实现大角度旋转下的真实渲染。ExpanDyNeRF通过优化密度与颜色特征，提升困难视角下的场景重建效果。我们还构建了首个带有显式侧视监督的合成多视角动态场景数据集SynDM，其通过自研GTA V渲染管线生成。在SynDM及真实数据集上的定量与定性结果表明，ExpanDyNeRF在极端视角偏移下显著优于现有动态NeRF方法，渲染保真度大幅提升。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。