PruneGround: 用于3D视觉定位的即插即用空间剪枝框架
PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding
AI总结：
提出PruneGround框架，通过语言引导的空间剪枝、多视角描述重构和LLM定位器，在剪枝区域高效定位目标，在多个基准上取得最优结果。
摘要：
3D视觉定位（3DVG）旨在根据自然语言描述在3D场景中定位目标对象。现有方法通常对整个场景进行推理，导致预测模糊且计算成本高，尤其是在杂乱环境中。我们观察到许多指代表达依赖于局部空间上下文，且通常对应受限的空间区域而非整个场景。基于这一洞察，我们提出PruneGround，一个基于三个关键组件的有效即插即用3DVG框架。首先，我们引入语言引导的空间剪枝（LGSP），利用冻结的视觉语言模型（VLM）识别与语言相关的区域，从而减少空间计算并在更窄的搜索空间中定位候选对象。其次，我们提出多视角条件描述重构（MCDR），将复杂表达分解为简化的目标-锚点关系，并通过多视角推理增强缺失的空间线索。最后，我们提出LLM-Grounder，通过将点云和语言表示在剪枝区域内对齐，将检测预训练的空间大语言模型（LLM）重新用作语言条件定位模型。在三个最流行的点云基准上的大量实验表明，我们的方法在ScanRefer的所有三个设置以及Nr3D/Sr3D的10个设置中的9个上取得了最先进的结果。代码和模型已公开：this https URL
英文摘要：
3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions. Existing approaches typically perform reasoning over the entire scene, leading to ambiguous predictions and high computational cost, especially in cluttered environments. We observe that many referential expressions rely on local spatial context and often correspond to restricted spatial regions rather than the full scene. Motivated by this insight, we propose PruneGround, an effective plug-and-play framework for 3DVG built upon three key components. First, we introduce Language-Guided Spatial Pruning (LGSP), which leverages a frozen Vision Language Model (VLM) to identify language-relevant regions, thereby reducing spatial computation and grounding candidates in the narrower search space. Second, we propose MultiView-Conditioned Description Reformulation (MCDR), which decomposes complex expressions into simplified target--anchor relations and augments missing spatial cues through multi-view reasoning. Finally, we propose LLM-Grounder, which repurposes a detection-pretrained spatial LLM into a language-conditioned grounding model by aligning point cloud and linguistic representations within the pruned region. Extensive experiments on the three most popular point cloud benchmarks demonstrate that our method achieves state-of-the-art results on all three ScanRefer settings and on 9 out of 10 Nr3D/Sr3D settings. Code and models are publicly available: https://github.com/leduckhai/PruneGround
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
