Search papers, labs, and topics across Lattice.
The paper introduces SeGPruner, a novel visual token pruning framework for 3D question answering that addresses token redundancy in multi-view vision-language models. SeGPruner employs a two-stage approach: first, it uses an attention-based module to retain semantically salient tokens, and then it diversifies the token set using a geometry-guided selector based on semantic relevance and 3D geometric distance. Experiments on ScanQA and OpenEQA show that SeGPruner achieves significant improvements in inference efficiency, reducing the visual token budget by 91% and inference latency by 86%, while maintaining competitive performance.
Cut your 3D-QA model's token budget by 91% and latency by 86% with a new pruning method that intelligently balances semantic importance and geometric coverage.
Vision-language models (VLMs) have been widely adopted for 3D question answering (3D QA). In typical pipelines, visual tokens extracted from multiple viewpoints are concatenated with language tokens and jointly processed by a large language model (LLM) for inference. However, aggregating multi-view observations inevitably introduces severe token redundancy, leading to an overly large visual token set that significantly hinders inference efficiency under constrained token budgets. Visual token pruning has emerged as a prevalent strategy to address this issue. Nevertheless, most existing pruners are primarily tailored to 2D inputs or rely on indirect geometric cues, which limits their ability to explicitly retain semantically critical objects and maintain sufficient spatial coverage for robust 3D reasoning. In this paper, we propose SeGPruner, a semantic-aware and geometry-guided token reduction framework for efficient 3D QA with multi-view images. Specifically, SeGPruner first preserves semantically salient tokens through an attention-based importance module (Saliency-aware Token Selector), ensuring that object-critical evidence is retained. It then complements these tokens with spatially diverse ones via a geometry-guided selector (Geometry-aware Token Diversifier), which jointly considers semantic relevance and 3D geometric distance. This cooperation between saliency preservation and geometry-guided diversification balances object-level evidence and global scene coverage under aggressive token reduction. Extensive experiments on ScanQA and OpenEQA demonstrate that SeGPruner substantially improves inference efficiency, reducing the visual token budget by 91% and inference latency by 86%, while maintaining competitive performance in 3D reasoning tasks.
