LatentAM：通过在线字典学习实现实时、大规模的潜在高斯注意力映射
LatentAM: Real-Time, Large-Scale Latent Gaussian Attention Mapping via Online Dictionary Learning
AI总结：
LatentAM通过在线字典学习实现实时、大规模的潜在高斯注意力映射，提升机器人感知的特征重建保真度与实时性
摘要：
我们提出了LatentAM，一种在线3D高斯点云（3DGS）映射框架，该框架从流式RGB-D观测中构建可扩展的潜在特征图，用于开放词汇的机器人感知。与通过模型特定解码器蒸馏高维视觉-语言模型（VLM）嵌入不同，LatentAM提出了一种在线字典学习方法，该方法既模型无关又无需预训练，使能够与不同的VLM在测试时无缝集成。具体来说，我们的方法将每个高斯原语与一个紧凑的查询向量相关联，该向量可以通过带有可学习字典的注意力机制转换为近似的VLM嵌入。字典从流式观测中高效初始化，并在线优化以适应不断演变的场景语义，在信任区域正则化下进行优化。为了扩展到长轨迹和大环境，我们进一步提出了一种基于体素哈希的高效地图管理策略，其中优化被限制在GPU上的活跃局部地图，而全局地图存储并索引在CPU上，以维持有限的GPU内存使用。在公共基准和大规模自定义数据集上的实验表明，LatentAM在特征重建保真度方面显著优于最先进的方法，同时在评估数据集上实现了接近实时的速度（12-35 FPS）。我们的项目页面是：https://junwoonlee.github.io/projects/LatentAM
英文摘要：
We present LatentAM, an online 3D Gaussian Splatting (3DGS) mapping framework that builds scalable latent feature maps from streaming RGB-D observations for open-vocabulary robotic perception. Instead of distilling high-dimensional Vision-Language Model (VLM) embeddings using model-specific decoders, LatentAM proposes an online dictionary learning approach that is both model-agnostic and pretraining-free, enabling plug-and-play integration with different VLMs at test time. Specifically, our approach associates each Gaussian primitive with a compact query vector that can be converted into approximate VLM embeddings using an attention mechanism with a learnable dictionary. The dictionary is initialized efficiently from streaming observations and optimized online to adapt to evolving scene semantics under trust-region regularization. To scale to long trajectories and large environments, we further propose an efficient map management strategy based on voxel hashing, where optimization is restricted to an active local map on the GPU, while the global map is stored and indexed on the CPU to maintain bounded GPU memory usage. Experiments on public benchmarks and a large-scale custom dataset demonstrate that LatentAM attains significantly better feature reconstruction fidelity compared to state-of-the-art methods, while achieving near-real-time speed (12-35 FPS) on the evaluated datasets. Our project page, including the code, is available at: https://junwoonlee.github.io/projects/LatentAM
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。
