3DZip：空間感知特徵多樣性引導的Token壓縮方法用於3D問答

摘要

近期3D視覺語言模型（3D VLMs）透過將2D視覺特徵投影至世界座標來建構幾何感知令牌，從而實現如3D問答等任務的空間推理能力。然而，此設計會為每個場景產生數以千計的令牌，導致大量的計算與記憶體開銷。儘管令牌壓縮已在2D VLMs中被廣泛研究，現有方法依賴於語義相關性或注意力機制選擇，忽略了3D令牌的結構化空間特性。此外，3D表示中的冗餘無法僅靠空間鄰近性來解決，因為即使在空間聚合之後，物件層級的令牌不平衡問題依然存在。為了解決此問題，我們提出3DZip，一個三階段的令牌壓縮框架：首先應用粗粒度體素化以消除點級冗餘，接著透過行列式點過程基於特徵空間多樣性選取錨點令牌，最後在空間約束下合併剩餘令牌以保持幾何一致性。在三個3D問答基準測試上的實驗表明，3DZip始終優於現有的壓縮方法，僅使用128個令牌即可保留94.7%的原始性能，並實現1.92倍的推論加速。

English

Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering. However, this design generates thousands of tokens per scene, resulting in substantial computational and memory overhead. While token compression has been extensively studied in 2D VLMs, existing approaches rely on semantic relevance or attention-based selection that overlook the structured spatial nature of 3D tokens. Moreover, redundancy in 3D representations cannot be resolved by spatial proximity alone, as object-level token imbalance persists even after spatial aggregation. To address this, we propose 3DZip, a three-stage token compression framework that first applies coarse voxelization to remove point-level redundancy, then selects anchor tokens based on feature-space diversity via a Determinantal Point Process, and finally merges remaining tokens under spatial constraints to preserve geometric coherence. Experiments on three 3D question answering benchmarks demonstrate that 3DZip consistently outperforms existing compression methods, retaining 94.7% of the original performance with only 128 tokens, achieving a 1.92times faster inference speed.