一个世界，双时间线：解耦的空间-时间高斯场景图用于4D协同驾驶重建
One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction
AI总结：
本文提出DUST解耦空间-时间高斯场景图，解决车辆与基础设施相机时间不同步导致的动态场景重建问题，通过解耦姿态轨迹和静态锚点校正提升重建精度与鲁棒性。
摘要：
从车辆到基础设施协同自动驾驶（VICAD）数据中重建动态场景本质上受到时间异步性的阻碍：车辆和基础设施摄像头运行在独立时钟上，捕捉相同动态代理（如汽车和行人）在不同物理时间。现有高斯场景图方法隐式假设同步观测，并为每个代理每帧分配单一姿态，这一假设在协同设置中失效，导致严重的鬼影现象。我们将其视为表示层面的失败，而非优化 artifacts：我们证明任何单时间线方法都会产生与代理速度和跨源时间偏移平方成比例的不可消除的光度损失。为了解决这个问题，我们提出Dust（解耦空间-时间）高斯场景图用于4D协同驾驶重建。DUST高斯场景图为每个代理共享一个标准高斯集以保持外观一致性，同时保持解耦姿态轨迹，与每个源的真实捕获时间戳对齐。我们证明这种解耦使姿态梯度核成为块对角矩阵，完全消除跨源干扰。为使Dust实用，我们进一步引入基于静态锚点的姿态校正流程，校正车辆和基础设施注释之间的空间错位，并引入姿态正则化的联合优化方案，防止早期训练期间轨迹抖动和漂移。在26个V2X-Seq序列上，DUST实现了最先进的性能，比最强基线动态区域PSNR提高3.2 dB，Fréchet视频距离减少37.7%，在更大的时间异步性下保持鲁棒性。
英文摘要：
Reconstructing dynamic scenes from Vehicle-to-Infrastructure Cooperative Autonomous Driving (VICAD) data is fundamentally complicated by temporal asynchrony: vehicle and infrastructure cameras operate on independent clocks, capturing the same dynamic agent such as cars and pedestrians at different physical times. Existing Gaussian Scene Graph methods implicitly assume synchronized observations and assign a single pose per agent per frame, which is an assumption that breaks in cooperative settings, where the resulting gradient conflicts cause severe ghosting on dynamic agents. We identify this as a representation-level failure, not an optimization artifact: we prove that any single-timeline formulation incurs an irreducible photometric loss scaling quadratically with agent velocity and cross-source time offset. To resolve this, we propose Dust (DecoUpled Spatio-Temporal) Gaussian Scene Graph for 4D Cooperative Driving Reconstruction. DUST Gaussian Scene Graph shares a canonical Gaussian set per agent for appearance consistency, while maintaining decouple pose trajectories aligned to each source's true capture timestamps. We prove that this decoupling enables the pose-gradient kernel block-diagonal, eliminating cross-source interference entirely. To make Dust practical, we further introduce a static anchor-based pose correction pipeline that corrects spatio misalignment between vehicle and infrastructure annotations, and a pose-regularized joint optimization scheme that prevents trajectory jitter and drift during early training. On 26 sequences from V2X-Seq, DUST achieves state-of-the-art performance, improving dynamic-area PSNR by 3.2 dB over the strongest baseline and reducing Fréchet Video Distance by 37.7%, with keeping robustness under larger temporal asynchrony.
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。
