Scene Graphs

Follow this topic Ask about this topic

Latest papers

17 papers1 paper in the last four weeks, down 80% on the four weeks before. 0.0% of all new papers.

ChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning
Sep 30, 2026Chenyangguang Zhang, Malgorzata Gwiazda, Guanlong Jiao +5Graph-Based Planning 4D Scene Understanding
ETH Zurich · Technical University of Munich · University of British Columbia +3
HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models
Sep 15, 2026Yuchen Liu, Luigi Palmieri, Lujun Li +3Human-Robot Collaboration Robot Task Planning
University of Stuttgart, Germany · University of Luxembourg, Luxembourg · Bosch Center for Artificial Intelligence, Germany
ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions
Sep 14, 2026Xintong Fang, Zhiyuan Fang, Rengan Xie +63D SGG 3D Scene Generation
Zhejiang University, Hangzhou, China · State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China · Korea Advanced Institute of Science and Technology (KAIST) +1
Scene Graph-Driven Haptic Feedback for Safety Enhancement in Robotic Ophthalmic Surgery via Physically Simulated iOCT
Sep 7, 2026Danial Arbabi, Korab Hoxha, Angelo Henriques +2Haptic Feedback Scene Graphs
School of Medicine and Health, Department of Ophthalmology, TUM University Hospital, Technical University of Munich (TUM), Munich, Germany · Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM), Munich, Germany · Chair of Ergonomics, TUM School of Engineering and Design, Technical University of Munich (TUM), Munich, Germany +1
Commonsense Reasoning in Computer Vision: Foundations, Recent Advancements, and Future Directions
Sep 4, 2026Bahar Uddin Mahmud, Sumit Barua, Guan Yue Hong +2Scene Graphs Visually Grounded Reasoning
Lander University, Greenwood, SC, USA · Western Michigan University, Kalamazoo, MI, USA
ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation
Aug 25, 2026JooYoung Jang, Taegyeong Lee, Jihyeon Park +1Scene Graphs Language Model Editing
Seoul National University · Miridih
Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation
Jul 16, 2026Chi Kit Wong, Ye Pan, Yuanhuiyi Lyu +6Visual Question Answering Visual Spatial Reasoning
The Hong Kong University of Science and Technology (Guangzhou) · Guangxi Zhuang Autonomous Region Information Center · The Hong Kong University of Science and Technology
Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs
Jul 2, 2026Francesca Pistilli, Simone Alberto Peirone, Giuseppe AvertaScene Graph Generation Egocentric Video Understanding
Politecnico di Torino · Torino, Italy
Visual Commonsense Driven Knowledge Refinements for Scene Graph Generation
Jun 4, 2026Maëlic Neau, Salim Baloch, Jakob Suchan +2Scene Graph Generation Multimodal Reasoning
Computing Science Department, Umeå University, Umeå, Sweden · School of Computer Science & Engineering, Constructor University, Bremen, Germany · CoDesign Lab EU., Örebro, Sweden +1
SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models
May 13, 2026Vladislav Makarov, Mark Gizetdinov, Dmitry YudinScene Graph Generation Vision-Language Models
MIRAI · MIREA · MIRAI, AXXX
AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning
Apr 20, 2026Junxiao Xue, Quan Deng, Tingqi Hu +4Multimodal RAG Visual Question Answering
Research Center for Space Computing System, Zhejiang Lab, Hangzhou 311100, China · Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 311000, China · School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, China +1
Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching
Apr 18, 2026Xin Hu, Ke Qin, Wen Yin +3Scene Graph Generation Flow Matching
The Laboratory of Intelligent Collaborative Computing of UESTC · Monash University · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)
CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research
Apr 8, 2026Carlos Caetano, Camila Laranjeira, Clara Ernesto +5Scene Graphs Image Classification
Universidade Estadual de Campinas (UNICAMP), Brazil · Instituto Federal de Educação, Ciência e Tecnologia de Minas Gerais (IFMG), Brazil · Universidade de São Paulo (USP), Brazil +3
Towards Spatio-Temporal World Scene Graph Generation from Monocular Videos
Mar 13, 2026Rohith Peddi, Saurabh, Shravan Shanmugam +4Scene Graphs Video SGG
The University of Texas at Dallas, Richardson, TX 75080, USA · Indian Institute of Technology Delhi, New Delhi, India
Sampling-Based Motion Planning with Scene Graphs Under Perception Constraints
Mar 3, 2026Qingxi Meng, Emiliano Flores, Thai Duong +2Scene Graphs Motion Planning
Department of Computer Science, Rice University, Houston, TX 77005 USA · the Department of Computer Science, Rice University, Houston, TX 77005 USA, and also with Ken Kennedy Institute, Rice University, Houston, TX 77005 USA.
Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos
Feb 26, 2026Ziqi Gao, Jieyu Zhang, Wisdom Oluchi Ikezogwo +10Video SGG Scene Graph Generation
Allen Institute for AI · University of Washington · Microsoft +1
Generated Contents Enrichment
May 6, 2024Mahdi Naseri, Jiayan Qiu, Zhou WangScene Graph Generation Conditional Image Generation
University of Waterloo, Department of Electrical and Computer Engineering, Waterloo, ON, Canada

Sep 30, 2026J/K move · Enter open · S save

ChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning

Chenyangguang Zhang, Malgorzata Gwiazda, Guanlong Jiao, Yuanchen Ju+4

ETH Zurich · Technical University of Munich · University of British Columbia+3

Graph-Based Planning 4D Scene Understanding VLMs for Robotics Scene Graphs

Open paper AskPDF arXiv

Embodied agents must determine where to act, anticipate the resulting scene changes, and interpret observed outcomes to guide subsequent actions. This requires connecting 4D interaction understanding, which explains how past actions changed the scene, with spatially grounded planning, which determines how and where to act toward a goal and anticipates the resulting scene changes. We introduce ChronoGraph, a functional 4D scene graph that links actions on affordance parts to semantic and geometric state changes. By representing observed and anticipated transitions in the same form, it provides a shared basis for understanding and planning. We construct ChronoGraphBench through an automatic data engine that converts human-interaction videos and simulated robot trajectories into graph-annotated questions for training and evaluating Vision-Language Models (VLMs) on both tasks. Using these annotations, we train ChronoGraphVLM by adapting pretrained VLMs in two stages. Graph-as-Chain-of-Thought supervised fine-tuning teaches the models to reconstruct observed transitions and predict future ones as graph traces before answering. Subsequent joint 4D graph reinforcement learning directly rewards graph properties and answer correctness. Experiments across model scales show improvements over the corresponding pretrained baselines and zero-shot transfer to VLM4D. Real-world demonstrations further show that graph-based planning and affordance grounding support mobile manipulation through existing robot skills without additional fine-tuning.