CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs

2026-09-08

AI Summary

为解决多视角3D推理中视觉令牌冗余问题，提出CoVeR方法，通过仅使用令牌坐标选择覆盖场景各区域的令牌，实现精确预算控制并提高3D推理性能。

Abstract

Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sidestepping the scarcity of annotated 3D data. However, it produces thousands of redundant visual tokens whose cost grows with every view. Existing visual token pruners fall into two families, each limited in the 3D multi-view setting. Learned importance methods rank tokens by attention or encoder features; because redundancy here is fundamentally spatial, they keep near-duplicate tokens from a few prominent regions and leave most of the scene unrepresented. Voxelization methods improve spatial coverage but cannot enforce an exact token budget and saturate as multi-view observations overlap in 3D, capping retention well below the target. We show that spatial coverage is associated with 3D reasoning performance and introduce CoVeR, a deterministic, training-free selector that uses only token coordinates, with no learned signals. CoVeR selects tokens that collectively cover every region of the scene, and solves the limitations of both families: it enforces an exact per-scene budget, breaks the voxelization saturation plateau, and avoids the near-duplicate selections of learned importance. Extensive experiments show CoVeR outperforms prior SOTAs on all three 3D reasoning benchmarks and generalizes as a plug-and-play module tested across four VLMs. Notably, with only $\approx$8% of visual tokens, it preserves 93.5% of full-token performance, surpassing SOTA by 3.9 percentage points on average across benchmarks.

Problem

• multi-view 3D reasoning
• visual token pruning
• spatial coverage

Innovation

• Coverage-Based Token Pruning
• Multi-View 3D Reasoning
• Spatial Coverage
• Token Budget
• Plug-and-Play Module