发表机构
Hong Kong University of Science and Technology; Hong Kong University of Science and Technology (Guangzhou)（香港科技大学; 香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对开放集3D形状检索中几何与外观特征融合问题，提出GATE-3D轻量级查询自适应重排方法，通过捕捉模态不一致特征预测分数调整排名，实验表明该方法优于外观检索且更稳健，提升了mAP等指标，还发现线性路由在低数据时更有效。
AI 中文摘要
大型预训练视觉模型显著改进了基于外观的3D形状检索，但仍会混淆外观相似但几何形状不同的形状。尽管几何感知特征可减少这些错误，但当两种模态已良好对齐时，简单融合几何和外观可能损害检索效果。我们提出GATE-3D，一种轻量级查询自适应重排方法，无需重新训练检索主干即可纳入几何信息。对于每个查询，GATE-3D使用捕捉两种模态间不一致的特征预测几何感知分数应如何调整基于外观的排名。这种选择性设计使几何信息在有帮助时起作用，在有损害时保持沉默。在三个开放集3D检索基准上的实验表明，GATE-3D优于仅基于外观的检索，且比始终融合更稳健。在主要基准上，它比仅基于外观的检索将mAP@10提高了2.00分（p=0.041）；还改善了留一类别出泛化，并将几何误报减少了10.8%。GATE-3D在与基于DAC的基线对比中取得了有竞争力的零样本结果。我们还发现，在低数据情况下，简单线性路由比小MLP更有效，这表明跨模态不一致特征在自适应路由中比模型容量更重要。
英文摘要
Large pretrained vision models have substantially improved appearance-based 3D shape retrieval, but they still confuse shapes that look similar while differing in geometry. Although geometry-aware features can reduce these errors, naive fusion of geometry and appearance may hurt retrieval when the two modalities are already well aligned. We propose GATE-3D, a lightweight query-adaptive reranking method that incorporates geometry without retraining the retrieval backbone. For each query, GATE-3D predicts how much a geometry-aware score should adjust the appearance-based ranking using features that capture disagreement between the two modalities. This selective design lets geometry contribute where it helps and stay silent where it would hurt. Experiments on three open-set 3D retrieval benchmarks show that GATE-3D improves over appearance-only retrieval and is more robust than always-on fusion. On the primary benchmark, it improves mAP@10 by 2.00 points over appearance-only retrieval (p=0.041); it also improves leave-one-category-out generalization and reduces geometric false positives by 10.8%. GATE-3D achieves competitive zero-shot results against DAC-based baselines. We further find that simple linear routing is more effective than a small MLP in the low-data regime, suggesting that cross-modal disagreement features matter more than model capacity for adaptive routing.
