流式高斯编码用于4D全景占据跟踪
Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking
AI总结：
提出流式高斯编码器，通过持久化场景表示和置信度引导的预算约束，实现相机4D全景占据跟踪，在nuScenes和Waymo上达到新最优。
摘要：
基于相机的4D全景占据跟踪（4D-POT）是一种有前景的范式，用于从多视角图像进行整体场景理解，能够跨时间联合推理几何、语义和物体身份。最近的基于掩码的管道通过跨帧传播实例查询实现了强大性能。然而，其底层体积表示通常在每个时间步重新计算，限制了几何时间一致性，特别是在遮挡和静态场景元素下。为解决这一限制，我们提出了一种流式高斯编码器，为4D-POT维护持久的体积场景表示。我们的方法将场景建模为固定大小的潜在高斯查询集，通过自我运动补偿传播，并在置信度引导的预算约束下刷新。关键地，我们通过深度监督塑造高斯不透明度作为可见性的代理，使置信度作为持久场景支持的时间聚合度量累积。结合基于预热的多帧训练策略，这产生了超越仅解码器跟踪的表示级时间一致性。在Occ3D扩展的nuScenes和Waymo上的大量实验建立了基于相机的4D-POT的新最先进水平，以可忽略的计算开销提高了跟踪一致性，同时与现有基于掩码的管道完全兼容。我们在该网址提供代码和模型。
英文摘要：
Camera-based 4D panoptic occupancy tracking (4D-POT) is a promising paradigm for holistic scene understanding from multi-view imagery, enabling joint reasoning about geometry, semantics, and object identities across time. Recent mask-based pipelines achieve strong performance by propagating instance queries across frames. However, their underlying volumetric representations are typically recomputed at each timestep, limiting geometric temporal consistency, particularly under occlusion and for static scene elements. To address this limitation, we propose a streaming Gaussian encoder that maintains a persistent volumetric scene representation for 4D-POT. Our method models the scene as a fixed-size set of latent Gaussian queries that are propagated via ego-motion compensation and refreshed under a confidence-guided budget constraint. Crucially, we shape Gaussian opacities through depth-based supervision to serve as proxy for visibility, enabling confidence to accumulate as a temporally aggregated measure of persistent scene support. Together with a warmup-based multi-frame training strategy, this yields representation-level temporal coherence beyond decoder-only tracking. Extensive experiments on Occ3D-extended nuScenes and Waymo establish a new state-of-the-art for camera-based 4D-POT, improving tracking consistency with negligible computational overhead while remaining fully compatible with existing mask-based pipelines. We provide code and models at https://sge.cs.uni-freiburg.de.
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。
