SSR3D-LLM: 通过潜在步骤实现结构化空间推理以实现统一3D-LLM中的细粒度定位
SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs
AI总结：
针对统一3D-LLM中细粒度查询的脆弱性，提出SSR3D-LLM，通过潜在空间推理步骤和几何感知评分器逐步精炼候选排名，在多个基准上取得最优结果。
摘要：
3D物体定位从自然语言中定位3D场景中的所指对象。统一的以实例为中心的3D-LLM旨在同时解决定位、对话、问答和描述任务，但许多方法依赖于单一的指针式定位决策，将关系指令压缩为一个选择。这对于需要根据上下文对象和空间关系排除多个同类候选的细粒度查询来说是脆弱的。我们提出结构化空间推理3D-LLM（SSR3D-LLM），一种用于统一3D-LLM的结构化定位接口。给定固定的Mask3D物体提议，LLM从查询中写出一系列潜在的空间推理步骤和记忆令牌，然后一个几何感知评分器读取这些潜在步骤，通过逐步长度掩码逐步精炼候选排名。潜在步骤从标准基准目标监督和训练期间的辅助指代线索监督中学习，而推理仅使用输入查询和Mask3D提议。在ReferIt3D、ScanRefer和Multi3DRef上，SSR3D-LLM在统一3D-LLM基线中取得了最强结果，在细粒度定位上相比单指针QPG基线有显著提升，并相比先前的统一3D-LLM有一致改进，同时保留了默认的语言任务路径。
英文摘要：
3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning, yet many rely on a single pointer-style grounding decision that compresses a relational instruction into one selection. This is brittle for fine-grained queries where multiple same-class candidates must be ruled out by context objects and spatial relations. We propose Structured Spatial Reasoning 3D-LLM (SSR3D-LLM), a structured grounding interface for unified 3D-LLMs. Given fixed Mask3D object proposals, the LLM writes a sequence of latent spatial reasoning steps and memory tokens from the query, and a geometry-aware scorer reads these latent steps in order to refine candidate rankings step by step with step-length masking. The latent steps are learned from standard benchmark target supervision with auxiliary referential-cue supervision during training, while inference uses only the input query and Mask3D proposals. Across ReferIt3D, ScanRefer, and Multi3DRef, SSR3D-LLM achieves the strongest results among unified 3D-LLM baselines, with substantial gains over the single-pointer QPG baseline on fine-grained grounding and consistent improvements over prior unified 3D-LLMs, while preserving the default language-task route.
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。
