用神经体素替代重复高斯点，实现动态场景高效渲染
4D Neural Voxel Splatting: Dynamic Scene Rendering with Voxelized Guassian Splatting
- 用可学习形变场的神经体素建模时间动态，避免每帧复制高斯点
- 内存消耗降低显著，训练速度更快，仍保持高质量图像
- 新增视图优化阶段，针对性提升难视角渲染效果
尽管3D高斯点阵（3D-GS）在新视角合成中实现了高效渲染，但将其扩展到动态场景时，仍因跨帧复制高斯点导致巨大内存开销。为此，我们提出4D神经体素点阵（4D-NVS），将体素表示与神经高斯点阵结合，实现高效的动态场景建模。该方法不再为每个时间戳生成独立的高斯集合，而是采用一组紧凑的神经体素搭配学习得到的形变场来建模时间动态。该设计大幅降低内存占用并加速训练过程，同时保持高图像质量。我们进一步引入一种新颖的视图精炼阶段，通过有针对性的优化，提升具有挑战性的视角渲染效果，在保持全局效率的同时增强困难视角的视觉质量。实验表明，本方法在显著减少内存消耗和加快训练速度的同时，实现了优于现有最优方法的实时渲染性能，并具备更优的视觉保真度。
原文摘要 · Abstract (English)
Although 3D Gaussian Splatting (3D-GS) achieves efficient rendering for novel view synthesis, extending it to dynamic scenes still results in substantial memory overhead from replicating Gaussians across frames. To address this challenge, we propose 4D Neural Voxel Splatting (4D-NVS), which combines voxel-based representations with neural Gaussian splatting for efficient dynamic scene modeling. Instead of generating separate Gaussian sets per timestamp, our method employs a compact set of neural voxels with learned deformation fields to model temporal dynamics. The design greatly reduces memory consumption and accelerates training while preserving high image quality. We further introduce a novel view refinement stage that selectively improves challenging viewpoints through targeted optimization, maintaining global efficiency while enhancing rendering quality for difficult viewing angles. Experiments demonstrate that our method outperforms state-of-the-art approaches with significant memory reduction and faster training, enabling real-time rendering with superior visual fidelity.
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。