MiKASA：用于3D视觉定位的多关键锚点与场景感知Transformer
MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding
AI总结：
针对3D视觉定位中多锚点和视角依赖查询理解困难的问题，本文提出端到端MiKASA Transformer，通过场景感知编码器与多关键锚点技术提升准确率、空间理解和可解释性，并在Sr3D与Nr3D上取得最优结果。
摘要：
3D视觉定位涉及将自然语言描述与3D空间中的相应对象进行匹配。现有方法在对象识别准确性方面常面临挑战，并且难以理解复杂的语言查询，尤其是涉及多个锚点或依赖视角的描述。为此，我们提出了MiKASA（Multi-Key-Anchor Scene-Aware，多关键锚点场景感知）Transformer。我们新颖的端到端训练模型集成了基于自注意力的场景感知对象编码器和原创的多关键锚点技术，提升了对象识别准确性和对空间关系的理解。此外，MiKASA提高了决策的可解释性，便于错误诊断。我们的模型在Referit3D挑战赛的Sr3D和Nr3D数据集上均取得最高总体准确率，尤其在需要依赖视角描述的类别中以大幅优势表现突出。
英文摘要：
3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique, enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore, MiKASA improves the explainability of decision-making, facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets, particularly excelling by a large margin in categories that require viewpoint-dependent descriptions.
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。
