LSVG：面向3D视觉定位的具有2D辅助多模态编码的语言引导场景图
LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding
AI总结：
本文提出LSVG框架，通过构建具有被指称物体判别能力的语言引导场景图，并结合2D辅助的双分支视觉编码与图注意力机制，提升3D视觉定位中相似物体区分和关系感知能力。
摘要：
3D视觉定位旨在根据自然语言描述在3D场景中定位唯一的目标物体。3D模态与语言模态之间的显著差距，使得通过所描述的空间关系区分多个相似物体成为一项突出挑战。当前方法试图通过以目标为中心的学习机制在复杂场景中实现跨模态理解，但忽略了对被指称物体的建模。我们提出了一种新颖的3D视觉定位框架，该框架构建具有被指称物体判别能力的语言引导场景图，以提升关系感知能力。该框架包含一个双分支视觉编码器，利用预训练的2D语义来增强并监督多模态3D编码。此外，我们采用图注意力机制在跨模态交互中促进面向关系的信息融合。学习到的物体表示和场景图结构使得3D视觉内容与文本描述之间能够有效对齐。在常用基准上的实验结果表明，与最先进方法相比，我们具有更优越的性能，尤其是在处理多个相似干扰物的挑战方面。
英文摘要：
3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the described spatial relationships. Current methods attempt to achieve cross-modal understanding in complex scenes via a target-centered learning mechanism, ignoring the modeling of referred objects. We propose a novel 3D visual grounding framework that constructs language-guided scene graphs with referred object discrimination to improve relational perception. The framework incorporates a dual-branch visual encoder that leverages pre-trained 2D semantics to enhance and supervise the multi-modal 3D encoding. Furthermore, we employ graph attention to promote relationship-oriented information fusion in cross-modal interaction. The learned object representations and scene graph structure enable effective alignment between 3D visual content and textual descriptions. Experimental results on popular benchmarks demonstrate our superior performance compared to state-of-the-art methods, especially in handling the challenges of multiple similar distractors.
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。
