场景作为标记：多尺度正常分布变换标记器用于通用3D视觉-语言理解
Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding
AI总结：
NDTokenizer3D通过多尺度NDT表示和解码器实现通用3D视觉-语言理解，提升3D场景任务性能。
摘要：
最近3D视觉-语言模型（VLMs）的进步突显了3D场景理解和推理的强大潜力。然而，有效地将3D场景整体标记化，并利用这些标记在多样化的3D理解任务中仍然极具挑战性。我们提出了NDTokenizer3D，一个通用的3D VLM，能够执行多种3D场景理解任务，同时自然支持人机交互，从而将语言层面的推理与3D空间理解联系起来。我们的方法核心是一种基于多尺度正常分布变换（NDT）表示的新型三阶段场景标记化流程，配以多尺度NDT解码器（MSDec）。具体而言，NDTokenizer3D首先从原始高分辨率点云构建多尺度NDT表示，保留全局上下文和细粒度几何细节。接下来，MSDec逐步融合跨尺度NDT特征，生成可供LLM端点消耗的完整场景标记。除了标记化外，MSDec被重新利用为人机交互提示（点、框、掩码）和分割-掩码解码的一般接口，将多种3D场景理解任务统一在单一架构中。凭借这种紧凑且统一的设计，NDTokenizer3D提供了一种细粒度、通用的3D VLM，实现了在3D指称分割、3D视觉问答和3D密集标注中的显著改进。
英文摘要：
Recent advances in 3D vision-language models (VLMs) highlight a strong potential for 3D scene understanding and reasoning. However, effectively tokenizing 3D scenes into holistic scene tokens, and leveraging these tokens across diverse 3D understanding tasks, remain highly challenging. We present NDTokenizer3D, a generalist 3D VLM that performs a wide range of 3D scene understanding tasks while naturally supporting human interactions, thereby bridging language-level reasoning with 3D spatial understanding. The core of our approach is a novel three-stage scene tokenization pipeline built upon a Multi-Scale Normal Distributions Transform (NDT) representation, paired with a Multi-Scale NDT Decoder (MSDec). Specifically, NDTokenizer3D first constructs a multi-scale NDT representation from raw high-resolution point clouds, preserving both global context and fine-grained geometric details. Next, the MSDec progressively fuses cross-scale NDT features, producing holistic scene tokens consumable by LLM endpoints. Beyond tokenization, MSDec is repurposed as a general interface for human-interactive prompting (points, boxes, masks) and segmentation-mask decoding, unifying diverse 3D scene understanding tasks within a single architecture. With this compact and unified design, NDTokenizer3D offers a fine-grained, general-purpose 3D VLM, achieving remarkable improvements in 3D Referring Segmentation, 3D Visual Question Answering, and 3D Dense Captioning.
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。
