paper-with-me

Papers

Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation

2024-03-18 · Ming Xu, Zilong Xie

Most Vision-and-Language Navigation (VLN) algorithms are prone to making inaccurate decisions due to their lack of visual common sense and limited reasoning capabilities. To address this issue, we propose a Hierarchical Spatial Proximity Reasoning (HSPR) method. First, we introduce a scene understanding auxiliary task to help the agent build a knowledge base of hierarchical spatial proximity. This task utilizes panoramic views and object features to identify types of nodes and uncover the adjacency relationships between nodes, objects, and between nodes and objects. Second, we propose a multi-step reasoning navigation algorithm based on the hierarchical spatial proximity knowledge base, which continuously plans feasible paths to enhance exploration efficiency. Third, we introduce a residual fusion method to improve navigation decision accuracy. Finally, we validate our approach with experiments on publicly available datasets including REVERIE, SOON, R2R, and R4R. Our code is available at https://github.com/iCityLab/HSPR

📄 PDF Abstract BibTeX arXiv:2403.11541

Code (2)

18979705623/hspr 공식 구현 pytorch
icitylab/hspr 공식 구현 pytorch

Tasks

Common Sense ReasoningEfficient ExplorationScene UnderstandingVision and Language Navigation

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models

2024-12-17 · Wenyu Zhang, Wei En Ng, Lixin Ma, Yuwen Wang 외

Current vision-language models may incorporate single-dimensional spatial cues, such as depth, object boundary, and basic spatial directions (e.g. left, right, front, back), yet often lack the multi-dimensional spatial r…

Logical ReasoningSpatial Reasoning

CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models

2026-04-21 · Shengli Zhou, Xiangchen Wang, Guanhua Chen, Feng Zheng arxiv

Large language models (LLMs) have recently been applied to 3D vision-language (3D-VL) tasks, which require spatial reasoning to identify target objects relative to anchors. Scene graphs are commonly employed to represent…

Spatial Reasoning

Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT

2026-05-10 · Alaa Asfour, Christopher Indris, Leihan Chen, Tejas Vyas 외 arxiv

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial …

Knowledge DistillationSpatial ReasoningAnswer GenerationDepth Estimation

Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning

2025-10-03 · Chashi Mahiul Islam, Oteo Mamo, Samuel Jacob Chacko, Xiuwen Liu 외 arxiv

Vision-language models (VLMs) have advanced multimodal reasoning but still face challenges in spatial reasoning for 3D scenes and complex object configurations. To address this, we introduce SpatialViLT, an enhanced VLM …

Multimodal ReasoningMulti-Task LearningSpatial Reasoning

SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning

2026-03-28 · Jian Zhang, Shijie Zhou, Bangya Liu, Achuta Kadambi 외 arxiv

Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geomet…

Spatial Reasoning