发表机构
School of Computer Science, Henan Institute of Science and Technology（河南科技学院计算机学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有3DGS指称分割方法依赖相似度匹配的缺陷，提出QAGaussian框架，经Mosaic3D-5.6M预训练后，在基准上实现性能提升，优于现有最强基线。
AI 中文摘要
3D高斯溅射（3DGS）中的开放词汇指称分割要求神经模型根据自由形式的语言表达式选择高斯基元。现有基于3DGS的方法通常依赖全局文本-区域相似度，对于涉及属性、参考对象、空间关系和细粒度部件的查询而言效果较弱，这常导致目标-参考混淆、粒度不匹配、部件-整体泄露和关系违规。我们提出QAGaussian，一种用于语言引导的高斯基元选择的查询自适应神经推理框架。QAGaussian首先学习查询条件下的多尺度高斯插槽作为可微候选，其感受野由输入表达式塑造；随后构建关系感知插槽图，采用语言条件下的边权重来传播目标-参考、属性、部件-整体和上下文证据。粒度自适应路由器柔和地结合区域级、对象级、部件级、属性感知和关系感知掩码分支，再进行关系约束的细化以实现空间、部件-整体、属性和几何一致性。QAGaussian仅在Mosaic3D-5.6M上进行预训练以实现高斯-文本对齐，并在独立基准上进行评估，未针对目标数据集进行微调。它取得了47.2的平均mIoU和63.2的平均F1，比最强的3DGS指称基线分别高出2.7个mIoU点和2.9个F1点；还将部件mIoU从38.6提升至43.4，关系mIoU从44.4提升至50.8，并将目标-参考混淆从10.8降至7.4。这些结果表明，查询条件插槽学习、关系感知图推理和自适应路由为3DGS中的开放词汇指称分割提供了有效的神经建模策略。代码可在该https URL获取。
英文摘要
Open-vocabulary referring segmentation in 3D Gaussian Splatting (3DGS) requires a neural model to select Gaussian primitives according to free-form language expressions. Existing 3DGS-based methods usually rely on global text-region similarity, which is weak for queries involving attributes, reference objects, spatial relations, and fine-grained parts. This often causes target-reference confusion, granularity mismatch, part-whole leakage, and relation violations. We propose QAGaussian, a query-adaptive neural reasoning framework for language-guided Gaussian primitive selection. QAGaussian first learns query-conditioned multi-scale Gaussian slots as differentiable candidates whose receptive fields are shaped by the input expression. It then builds a relation-aware slot graph with language-conditioned edge weighting to propagate target-reference, attribute, part-whole, and contextual evidence. A granularity-adaptive router softly combines region-level, object-level, part-level, attribute-aware, and relation-aware mask branches, followed by relation-constrained refinement for spatial, part-whole, attribute, and geometric consistency. QAGaussian is pretrained only on Mosaic3D-5.6M for Gaussian-text alignment and evaluated on independent benchmarks without target-dataset fine-tuning. It achieves 47.2 Avg. mIoU and 63.2 Avg. F1, outperforming the strongest 3DGS referring baseline by 2.7 mIoU points and 2.9 F1 points. It also improves Part-mIoU from 38.6 to 43.4, Rel-mIoU from 44.4 to 50.8, and reduces target-reference confusion from 10.8 to 7.4. These results demonstrate that query-conditioned slot learning, relation-aware graph reasoning, and adaptive routing provide an effective neural modeling strategy for open-vocabulary referring segmentation in 3DGS. The code is available at https://github.com/zqeslwyz/QAGaussian.
Comments24 pages, 5 figures
