外观
论文arXiv 2610.2120713 天前
SpaceCache：用于点云流高效语义分割的中间特征复用
原文链接：SpaceCache: Intermediate Feature Reuse for Efficient Semantic Segmentation on Point Cloud Streams（arXiv 2610.21207 · 发布日期：2026-10-15）
SpaceCache: Intermediate Feature Reuse for Efficient Semantic Segmentation on Point Cloud Streams
SpaceCache针对点云流逐帧重复计算问题，以免训练特征缓存复用Transformer中间特征，并在室内外基准验证加速效果。
核心要点
- 点云流在自动驾驶和机器人中重要，但现有分割网络每帧从头处理。
- SpaceCache复用同一区域跨帧语义一致的中间特征，使已观察token跳过部分Transformer块。
- 缓存管理通过限制条目年龄、淘汰低置信条目，保持复用特征可靠。
- 在nuScenes、Waymo、ScanNet上最高1.65倍加速，mIoU降幅小于1点。
验证范围与局限：验证范围为nuScenes、Waymo、ScanNet室内外基准及Utonia、LitePT-B两种Transformer骨干。
英文摘要 (Abstract)
Point-cloud streams are central to autonomous driving and robotics, yet existing segmentation networks process every frame from scratch, although consecutive frames largely overlap. We observe that the intermediate features of point-cloud transformers remain semantically consistent across frames for the same spatial region, especially in deep stages. Building on this, we present SpaceCache, a training-free feature cache that reuses these features across frames. Tokens of previously observed regions skip a sequence of transformer blocks and take their cached features, only the remaining tokens are computed, and the full token layout is restored for dense prediction. Lightweight cache management keeps reused features reliable by limiting each entry's age and evicting low-confidence entries. Unlike token merging, SpaceCache selects tokens at negligible cost and runs its cache operations once per encoder stage. On both outdoor and indoor benchmarks, such as nuScenes, Waymo, and ScanNet, with two transformer backbones of Utonia and LitePT-B, SpaceCache achieves up to 1.65x speedup with less than 1-point mIoU drop and consistently outperforms token-merging methods.
作者：Dongheon Yang, Beomseok Kang, Jae‐Joon Kim
来源
本页事实对应的公开页面，以原文为准。