通过动态评分与分层压缩，实现视频流3D重建的稳定低内存运行。
StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
- 用跨层轨迹分析提升关键帧评分可靠性，减少误删。
- 三阶段缓存压缩保留重要几何信息，重建精度提升12.3%。
- 无需训练，适合实时3D建图与边缘设备部署。
从连续视频流中重建稠密3D几何结构需在恒定内存预算下保持稳定推理。现有O(1)框架主要依赖‘纯淘汰’机制，因二元化令牌删除和局部单层评分噪声导致显著信息损失。为此，我们提出StreamCacheVGGT，一种无需训练的框架，通过两个协同模块重构缓存管理：跨层一致性增强评分（CLCES）和混合缓存压缩（HCC）。CLCES通过追踪Transformer层级中令牌重要性轨迹，利用顺序统计分析识别持续的几何显著性，缓解激活噪声。基于这些鲁棒评分，HCC超越简单淘汰，引入三阶段筛选策略，将中等重要令牌通过键向量流形上的最近邻分配合并至保留锚点。该方法有效保留了易被丢失的关键几何上下文。在五个基准数据集（7-Scenes, NRGBD, ETH3D, Bonn, KITTI）上的广泛评估表明，StreamCacheVGGT达到新SOTA，不仅在严格恒定成本约束下实现更优重建精度与长期稳定性，且性能超越现有方法12.3%以上。
原文摘要 · Abstract (English)
Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing $O(1)$ frameworks primarily rely on a ``pure eviction'' paradigm, which suffers from significant information destruction due to binary token deletion and evaluation noise from localized, single-layer scoring. To address these bottlenecks, we propose StreamCacheVGGT, a training-free framework that reimagines cache management through two synergistic modules: Cross-Layer Consistency-Enhanced Scoring (CLCES) and Hybrid Cache Compression (HCC). CLCES mitigates activation noise by tracking token importance trajectories across the Transformer hierarchy, employing order-statistical analysis to identify sustained geometric salience. Leveraging these robust scores, HCC transcends simple eviction by introducing a three-tier triage strategy that merges moderately important tokens into retained anchors via nearest-neighbor assignment on the key-vector manifold. This approach preserves essential geometric context that would otherwise be lost. Extensive evaluations on five benchmarks (7-Scenes, NRGBD, ETH3D, Bonn, and KITTI) demonstrate that StreamCacheVGGT sets a new state-of-the-art, delivering superior reconstruction accuracy and long-term stability while strictly adhering to constant-cost constraints.
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。