3D-DRES: 详细3D指称表达分割
3D-DRES: Detailed 3D Referring Expression Segmentation
AI总结：
3D-DRES通过引入DetailRefer数据集和DetailBase架构，提升3D视觉语言理解的细粒度分割能力。
摘要：
当前的3D视觉定位任务仅处理句子级别的检测或分割，这严重限制了自然语言表达中丰富的组合上下文推理的利用。为解决这一挑战，我们引入了详细的3D指称表达分割（3D-DRES）任务，该任务提供一个短语到3D实例的映射，旨在增强细粒度的3D视觉语言理解。为了支持3D-DRES，我们提出了DetailRefer，一个包含54,432个描述、涵盖11,054个不同对象的新型数据集。与以往数据集不同，DetailRefer实施了一种开创性的短语-实例标注范式，其中每个被引用的名词短语都被明确映射到其对应的3D元素。此外，我们引入了DetailBase，一个经过精心简化但效果显著的基线架构，支持在句子和短语层面的双模式分割。我们的实验结果表明，训练在DetailRefer上的模型不仅在短语层面分割上表现出色，还在传统3D-RES基准测试中显示出令人惊讶的改进。
英文摘要：
Current 3D visual grounding tasks only process sentence level detection or segmentation, which critically fails to leverage the rich compositional contextual reasonings within natural language expressions. To address this challenge, we introduce Detailed 3D Referring Expression Segmentation (3D-DRES), a new task that provides a phrase to 3D instance mapping, aiming at enhancing fine-grained 3D vision language understanding. To support 3D-DRES, we present DetailRefer, a new dataset comprising 54,432 descriptions spanning 11,054 distinct objects. Unlike previous datasets, DetailRefer implements a pioneering phrase-instance annotation paradigm where each referenced noun phrase is explicitly mapped to its corresponding 3D elements. Additionally, we introduce DetailBase, a purposefully streamlined yet effective baseline architecture that supports dual-mode segmentation at both sentence and phrase levels. Our experimental results demonstrate that models trained on DetailRefer not only excel at phrase-level segmentation but also show surprising improvements on traditional 3D-RES benchmarks.
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。
