提出可持续更新的动态场景表示方法，显著降低内存与带宽开销。
CD-NGP: A Fast Scalable Continual Representation for Dynamic Scenes
- 通过时空哈希编码实现参数复用，减少动态场景特征干扰。
- 训练内存低于14GB，流式传输仅需0.4MB/帧，优于多数在线基线。
- 适用于长时序动态视频重建，适合实时渲染与资源受限场景。
动态场景的新视角合成（NVS）在内存消耗、模型复杂度、训练效率和渲染质量方面面临持续挑战。离线方法虽能提供高保真度，但内存占用高且难以扩展；在线方法常以牺牲质量换取速度与紧凑性。本文提出持续学习框架——持续动态神经图形原语（CD-NGP），通过参数复用降低内存开销并提升可扩展性。为避免动态场景中特征干扰并提高渲染质量，该方法结合空间与时间哈希编码，紧凑地表示场景结构与运动模式。此外，我们构建了一个新数据集，包含多视角、长时序（超过1200帧）视频，涵盖刚性与非刚性运动，填补现有基准空白。CD-NGP在公开数据集与自建长视频数据集上均表现出色，显著提升可扩展性与重建质量：训练内存低于14GB，DyNeRF流式传输带宽仅需0.4MB/帧，远低于多数在线基线。
原文摘要 · Abstract (English)
Novel view synthesis (NVS) in dynamic scenes faces persistent challenges in memory consumption, model complexity, training efficiency, and rendering quality. Offline methods offer high fidelity but suffer from high memory usage and limited scalability, while online approaches often trade quality for speed and compactness. We propose Continual Dynamic Neural Graphics Primitives (CD-NGP), a continual learning framework that reduces memory overhead and enhances scalability through parameter reuse. To avoid feature interference in dynamic scenes and improve rendering quality, our method combines spatial and temporal hash encodings, which compactly represent scene structures and motion patterns. We also introduce a new dataset comprising multi-view, long-duration ($>1200$ frames) videos with both rigid and non-rigid motion, which is not found in existing benchmarks. CD-NGP is evaluated on public datasets and our long video dataset, demonstrating superior scalability and reconstruction quality. It significantly reduces training memory usage to <14GB and requires only 0.4MB/frame in streaming bandwidth on DyNeRF -- substantially lower than most online baselines.
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。