FastMap：通过位掩码建模实现实时语义地图补全
FastMap: Real-Time Semantic Map Completion via Bitwise Masked Modeling
AI总结：
FastMap提出轻量级两阶段框架，利用位级标记和掩码自编码器实现实时语义地图补全，在Gibson基准上显著提升性能，并支持目标导航。
摘要：
语义地图补全，即从部分观测中预测未观测区域的布局，是室内机器人导航的关键能力。现有方法要么依赖高维离散码本，导致内存膨胀，要么依赖迭代扩散采样，速度太慢，无法满足实时需求。我们提出FastMap，一个轻量级两阶段框架，用于补全自上而下的类别语义地图。首先，一个免查找的BitVAE利用语义地图固有的二值（one-hot）结构，将每个地图块压缩为紧凑的位级标记，得到一个0.41GB的模型，比先前的掩码建模基线小3.7倍。其次，一个掩码自编码器（MAE）风格的Transformer在单次前向传播中重建缺失标记，速度为0.011秒/地图。为支持目标目标导航，我们还引入了一种目标感知的掩码策略，在训练期间掩码目标类别，并基于可学习的类别嵌入进行条件生成，且不增加推理成本。在Gibson基准上，FastMap实现了34.10%的mIoU和45.84%的语义成功率（sSR），是之前最佳结果（21.88%）的两倍多，并在下游ObjectNav任务上达到83.8%的成功率，在比较的导航方法中最高。
英文摘要：
Semantic map completion, which predicts the layout of unobserved regions from partial observations, is a critical capability for indoor robot navigation. Existing approaches either rely on high-dimensional discrete codebooks that inflate memory, or on iterative diffusion sampling that is too slow for real-time use. We present FastMap, a lightweight two-stage framework for completing top-down categorical semantic maps. First, a lookup-free BitVAE exploits the inherently binary (one-hot) structure of semantic maps to compress each map patch into compact bitwise tokens, yielding a 0.41GB model that is 3.7 times smaller than the prior masked-modeling baseline. Second, a Masked AutoEncoder (MAE)-style transformer reconstructs missing tokens in a single forward pass at 0.011s/map. To support object goal navigation, we additionally introduce an object-aware masking strategy that masks the target category during training and conditions generation on a learnable category embedding, without adding inference cost. On the Gibson benchmark, FastMap achieves 34.10% mIoU and 45.84% semantic Success Rate (sSR), more than doubling the previous best (21.88%), and reaches 83.8% Success Rate on downstream ObjectNav, the highest among the compared navigation methods.
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。
