GA-VLN：面向高效视觉语言导航的几何感知鸟瞰图表示
GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation
将RGB-D输入投影到鸟瞰图空间并融合3D基础模型先验，为MLLM提供紧凑且几何一致的空间表示，可复用于需要高效空间推理的视觉语言任务。
原文依据 We construct BEV spatial maps from RGB-D inputs by projecting visual features into 3D space and aggregating them into an agent-centric layout
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管视觉语言导航（VLN）已取得显著进展，现有方法仍依赖密集RGB视频，产生过多图像块词元且缺乏显式空间结构，导致大量计算开销和有限的空间推理能力。为解决这些问题，我们引入几何感知鸟瞰图（GA-BEV）——一种紧凑的、基于3D的特征表示，将显式和隐式几何线索集成到基于多模态大语言模型（MLLM）的导航系统中。我们通过将视觉特征投影到3D空间并聚合为以智能体为中心的布局，从RGB-D输入构建鸟瞰图空间地图，在保持几何一致性的同时减少词元冗余。为进一步丰富几何理解，我们将预训练3D基础模型的特征融入鸟瞰图空间，注入从大规模3D重建任务中学到的结构先验。这些互补线索——显式的基于深度的投影和隐式的学习先验——共同产生紧凑但空间表达力强的表示，显著提升导航效率和性能。实验表明，我们的方法仅使用导航数据即达到最优结果，无需DAgger增强或混合VQA训练，证明了所提出的GA-VLN框架的鲁棒性和数据效率。
英文原文摘要 1376 字符
Despite significant progress in Vision-Language Navigation (VLN), existing approaches still rely on dense RGB videos that produce excessive patch tokens and lack explicit spatial structure, resulting in substantial computational overhead and limited spatial reasoning. To address these issues, we introduce the Geometry-Aware BEV (GA-BEV) --a compact, 3D-grounded feature representation that integrates both explicit and implicit geometric cues into multimodal large language model (MLLM)-based navigation systems. We construct BEV spatial maps from RGB-D inputs by projecting visual features into 3D space and aggregating them into an agent-centric layout that preserves geometric consistency while reducing token redundancy. To further enrich geometric understanding, we incorporate features from a pretrained 3D foundation model into the BEV space, injecting structural priors learned from large-scale 3D reconstruction tasks. Together, these complementary cues--explicit depth-based projection and implicit learned priors--yield compact yet spatially expressive representations that substantially improve navigation efficiency and performance. Experiments show that our method achieves state-of-the-art results using only navigation data, without DAgger augmentation or mixed VQA training, demonstrating the robustness and data efficiency of the proposed GA-VLN framework.