GHOST: 用于高效3D重建的几何层次化在线流式令牌驱逐
GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction
AI总结：
提出GHOST框架，利用模型自身的3D几何输出在线驱逐冗余令牌，在保持重建质量的同时将KV缓存减半并实现1.75倍加速。
摘要：
从长单目视频序列进行流式3D重建需要维护一个随序列长度线性增长的键值（KV）缓存，造成严重的内存瓶颈。现有方法要么将缓存截断为固定的一组锚帧，导致重建质量下降，要么依赖于对3D场景结构无关的注意力分数启发式方法，未能保留几何上有价值的令牌。为解决这些问题，我们提出GHOST（几何层次化在线流式令牌驱逐），一种无需训练的KV缓存管理框架，利用模型自身的3D几何输出在线驱逐冗余令牌。GHOST引入了三项相互增强的创新：层次化双层重要性评分方案、保护特殊令牌不被驱逐的特权机制，以及余弦相似度引导的逐层预算分配。在各种基准上的实验表明，GHOST在保持出色重建质量的同时，将KV缓存削减近一半，并且与最先进方法相比实现了1.75倍的推理加速。我们的代码可在 https://github.com/lokiniuniu/GHOST 获取。
英文摘要：
Streaming 3D reconstruction from long monocular video sequences requires maintaining a key-value (KV) cache that grows linearly with sequence length, creating a severe memory bottleneck. Existing approaches either truncate the cache to a fixed set of anchor frames, leading to reconstruction quality degradation, or rely on attention-score heuristics that are agnostic to 3D scene structure, failing to preserve geometrically valuable tokens. To address these problems, we present GHOST (Geometry-Hierarchical Online Streaming Token Eviction), a training-free KV cache management framework that exploits the model's own 3D geometry outputs to evict redundant tokens online. GHOST introduces three mutually reinforcing innovations: a hierarchical dual-level importance scoring scheme, a privilege mechanism that protects special tokens from eviction, and a cosine-similarity-guided layer-wise budget allocation. Experiments on various benchmarks show that GHOST preserves excellent reconstruction quality while cutting the KV cache by nearly half and delivering 1.75x faster inference compared to state-of-the-art methods. Our code is available at https://github.com/lokiniuniu/GHOST.
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。
