AI 中文总结
针对实时重建需求，改进的 VBGS 框架通过空间截断变分推理和改进重新分配，加速连续重建。在 NeRF 合成数据集上，RTX 3070 Ti 实现平均每帧延迟大幅降低，加速 1680 倍，且保持重建质量。
AI 中文摘要
实时重建是机器人技术和自主导航中许多应用的关键需求。变分贝叶斯高斯点云融合（VBGS）通过坐标上升变分推理（CAVI）实现无重放缓冲区的连续学习，但其对所有观测点的逐帧迭代使其在具有严格内存和延迟要求的实时应用中速度过慢。我们提出了改进的 VBGS，这是一个用于实时连续重建的加速框架。主要通过（i）空间截断变分推理和（ii）改进的重新分配来实现，后者使用转发、截断并消除了浪费的动态重新编译。在 NeRF 合成数据集上，在 RTX 3070 Ti 上，我们将平均每帧延迟从约 84.0 秒降低到约 0.050 秒，加速了 1680 倍，同时保持了重建质量。
英文摘要
On-the-fly reconstruction is a key requirement for many applications in robotics and autonomous navigation. Variational Bayes Gaussian Splatting (VBGS) enables continual learning without replay buffers using Coordinate Ascent Variational Inference (CAVI), but its per-frame iterations over all observed points make it too slow for real-time use with strict memory and latency requirements. We present ImprovedVBGS, an accelerated framework for on-the-fly continual reconstruction. This is achieved primarily through (i) spatially truncated variational inference, and (ii) improved reassignment that uses forwarding, truncation and eliminates wasteful dynamic recompilation. On the NeRF synthetic dataset, we reduce mean per-frame latency from ~84.0 s to ~0.050 s on an RTX 3070 Ti, a 1680x speed-up while maintaining reconstruction quality. We also improve novel-view synthesis quality using an exact renderer with no added training costs.
Comments5 pages, 4 figures. Technical Report. This introduces ImprovedVBGS, accelerated continual learning for 3D Gaussian Splatting based Reconstruction. Code available at [https://github.com/damanimc/ImprovedVBGS](https://github.com/damanimc/ImprovedVBGS)
