LongSplat：面向长序列图像的在线可泛化3D高斯泼溅
LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images
AI总结：
LongSplat提出基于高斯-图像表示的流式更新机制，通过增量融合与冗余压缩实现长序列图像的在线实时3D高斯重建，在保持实时性能的同时将高斯数量减少44%。
摘要：
3D高斯泼溅实现了高保真新视角合成，但其在在线长序列场景中的应用仍然受限。现有方法要么依赖缓慢的逐场景优化，要么无法提供高效的增量更新，从而阻碍了持续性能。本文提出了LongSplat，一个面向长序列图像输入的在线实时3D高斯重建框架。其核心思想是一种流式更新机制，该机制增量式地整合当前视角观测，同时选择性地压缩冗余的历史高斯。对该机制至关重要的是我们的高斯-图像表示（Gaussian-Image Representation，GIR），该表示将3D高斯参数编码为结构化的、类似图像的2D格式。GIR同时实现了当前视角与历史高斯的高效融合以及身份感知的冗余压缩。这些功能支持在线重建，并使模型能够适应长序列，而不会造成内存或计算成本的过度负担。此外，我们利用现有的图像压缩方法来引导生成更紧凑且更高质量的3D高斯。大量评估表明，LongSplat在实时新视角合成中实现了最先进的效率-质量权衡，在提供实时重建的同时，与现有的逐像素高斯预测方法相比，将高斯数量减少了44%。
英文摘要：
3D Gaussian Splatting achieves high-fidelity novel view synthesis, but its application to online long-sequence scenarios is still limited. Existing methods either rely on slow per-scene optimization or fail to provide efficient incremental updates, hindering continuous performance. In this paper, we propose LongSplat, an online real-time 3D Gaussian reconstruction framework designed for long-sequence image input. The core idea is a streaming update mechanism that incrementally integrates current-view observations while selectively compressing redundant historical Gaussians. Crucial to this mechanism is our Gaussian-Image Representation (GIR), a representation that encodes 3D Gaussian parameters into a structured, image-like 2D format. GIR simultaneously enables efficient fusion of current-view and historical Gaussians and identity-aware redundancy compression. These functions enable online reconstruction and adapt the model to long sequences without overwhelming memory or computational costs. Furthermore, we leverage an existing image compression method to guide the generation of more compact and higher-quality 3D Gaussians. Extensive evaluations demonstrate that LongSplat achieves state-of-the-art efficiency-quality trade-offs in real-time novel view synthesis, delivering real-time reconstruction while reducing Gaussian counts by 44\% compared to existing per-pixel Gaussian prediction methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
