paper-with-me

Papers

Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis

2026-07-06 · Xianhao Chen, Jiarui Hu, Yuanbo Yang, Xiyu Zhang, Tengyue Wang, Hujun Bao, Guofeng Zhang, Zhaopeng Cui arxiv

Open-vocabulary 3D scene understanding aims to segment 3D scenes beyond predefined categories by transferring semantic knowledge from vision-language models. Existing methods have advanced this task by lifting language-aligned 2D features into 3D, yet they often rely on context-independent semantic representations, leaving object relationships underexplored for contextual refinement. We propose RelGraphOV, a relationship-aware framework that uses 3D scene graphs to enhance open-vocabulary 3D understanding. Our method constructs relational scene graphs from multi-view observations by leveraging vision-language reasoning to infer object relationships and prune geometrically implausible connections, without manual relationship annotations. To aggregate relational context while avoiding feature interference, we introduce an Adaptive Gated Dual-Stream Contextual GAT that separates dense geometric features and semantic CLIP embeddings, performs edge-guided message passing, and adaptively fuses complementary semantics. A hierarchical contrastive objective further promotes instance-level consistency and category-level discrimination. Experiments on ScanNetV2, ScanNet200, ScanNet$++$, and Replica demonstrate strong performance and generalization ability. Project Page: https://cxavireh.github.io/relgraphov-projectpage

📄 PDF Abstract BibTeX arXiv:2607.05348

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Understanding

Similar Papers 제목 키워드 기반

End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting

2024-09-19 · Yongqi Wang, Shuo Yang, Xinxiao wu, Jiebo Luo

Open-vocabulary video visual relationship detection aims to expand video visual relationship detection beyond annotated categories by detecting unseen relationships between both seen and unseen objects in videos. Existin…

DecoderObjectobject-detectionObject Detection+5

Relationship-Aware Safety Unlearning for Multimodal LLMs

2026-03-15 · Vishnu Narayanan Anilkumar, Abhijith Sreesylesh Babu, Trieu Hai Vo, Mohankrishna Kolla 외 arxiv

Generative multimodal models can exhibit safety failures that are inherently relational: two benign concepts can become unsafe when linked by a specific action or relation (e.g., child-drinking-wine). Existing unlearning…

FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs

2025-10-10 · Yan Wang, Keyi Wang, Shanshan Yang, Jaisal Patel 외 arxiv

Going beyond simple text processing, financial auditing requires detecting semantic, structural, and numerical inconsistencies across large-scale disclosures. As financial reports are filed in XBRL, a structured XML form…

Information ExtractionMathematical Reasoning

Crowd Counting on Images with Scale Variation and Isolated Clusters

2019-09-09 · Haoyue Bai, Song Wen, S. -H. Gary Chan

Crowd counting is to estimate the number of objects (e.g., people or vehicles) in an image of unconstrained congested scenes. Designing a general crowd counting algorithm applicable to a wide range of crowd images is cha…

ClusteringCrowd Counting

Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations

2026-05-15 · Sheikh Tanvir Ahmed, Md. Tanvir Raihan arxiv

Understanding how objects relate to each other in space is fundamental to scene understanding, yet most contrastive pre-training approaches only model pairwise relationships, leaving richer compositional and multi-hop in…

Contrastive LearningScene UnderstandingQuestion Answering