提出QAGaussian框架，实现3D高斯点云的精准语义分割。
Beyond Similarity Matching: Structured Reasoning for Open-Vocabulary Referring Segmentation in 3DGS
- 通过查询自适应的多尺度高斯槽，动态生成候选区域。
- 构建关系感知图，提升属性、空间、部件等复杂语义理解能力。
- 无需微调即可在多个数据集上超越现有方法，适合3D场景理解任务。
3D高斯喷溅（3DGS）中的开放词汇指代分割需根据自由文本表达选择高斯原语。现有方法依赖全局文本-区域相似性，难以处理属性、参照物、空间关系和细粒度部件，常导致目标-参照混淆、粒度不匹配、部件-整体泄漏及关系违反。本文提出QAGaussian，一种查询自适应的神经推理框架，用于语言引导的高斯原语选择。首先学习查询条件下的多尺度高斯槽，其感受野由输入表达式决定；随后构建语言条件边权重的关系感知槽图，传播目标-参照、属性、部件-整体及上下文证据；再通过粒度自适应路由，软性融合区域、物体、部件、属性感知与关系感知掩码分支，并进行关系约束的精细化修正。QAGaussian仅在Mosaic3D-5.6M上预训练，未进行目标数据集微调，在独立基准上取得47.2平均mIoU、63.2平均F1，优于最强3DGS基线2.7 mIoU和2.9 F1。Part-mIoU从38.6提升至43.4，Rel-mIoU从44.4提升至50.8，目标-参照混淆率从10.8降至7.4。结果表明，查询条件槽学习、关系感知图推理与自适应路由构成有效建模策略。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。