Results 221 to 230 of about 90,374 (275)

Open-Scene Understanding-oriented 3D Scene Graph Generation

2025 IEEE International Conference on Multimedia and Expo (ICME)
Understanding complex 3D environments is essential for many computer vision and robotic applications, especially in highly dynamic open-scene scenarios. The 3D scene graph plays an important role in the comprehension of 3D environments.
Yuansu Hao, Fei Yu, Yanhao Wang, Yuehua Li, Quan Deng, Yuan Yu, Chen Huang, Nan Che   +7 more
semanticscholar   +2 more sources

3D Scene Graph Generation From Point Clouds

IEEE Transactions on Multimedia
Scene graph generation is a significant and challenging task for scene understanding. Most existing methods are confined to the 2D space (i.e. images) or additional use of segmentation information, while neglecting the richer spatial and geometric ...
Wenwen Wei, Ping Wei, Jialu Qin, Zhimin Liao, Shuaijie Wang, Xiang Cheng, Mei-qin Liu, Nanning Zheng   +7 more
semanticscholar   +2 more sources

Graph2Scene: Versatile 3D Indoor Scene Generation with Interaction-aware Scene Graph

2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Embodied artificial intelligence requires a wide variety of large-scale simulated environments for development. Previous scene reconstruction approaches based on multiview images can produce high-fidelity 3D scenes but lack diversity.
Minglin Chen, Rongkun Yang, Qibin Hu, Kaiwen Xue, Shunbo Zhou, Yulan Guo   +5 more
semanticscholar   +2 more sources

Scene Graph with 3D Information for Change Captioning

Proceedings of the 29th ACM International Conference on Multimedia, 2021
Change captioning aims to describe the differences in image pairs with natural language. It is an interesting task under-explored with two main challenges: describing the relative position relationship between objects correctly and overcoming the disturbances from viewpoint changes.
Zeming Liao, Qingbao Huang, Yu Liang, Mingyi Fu, Yi Cai 0001, Qing Li 0001   +5 more
openaire   +1 more source

Indoor and Outdoor 3D Scene Graph Generation Via Language-Enabled Spatial Ontologies

IEEE Robotics and Automation Letters, 2023
This letter proposes an approach to build 3D scene graphs in arbitrary indoor and outdoor environments. Such extension is challenging; the hierarchy of concepts that describe an outdoor environment is more complex than for indoors, and manually defining ...
Jared Strader, Nathan Hughes, William Chen, Alberto Speranzon, Luca Carlone   +4 more
semanticscholar   +1 more source

SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction

IEEE Workshop/Winter Conference on Applications of Computer Vision, 2023
In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships.
Sebastian Koch, P. Hermosilla, N. Vaskevicius, M. Colosi, Timo Ropinski   +4 more
semanticscholar   +1 more source

Collaboration on Scene Graph Based 3D Data

2007
Professional 3D digital content creation tools, like Alias Maya or discreet 3ds max, offer only limited support for a team of artists to work on a 3D model collaboratively. We present a scene graph repository system that enables fine-grained collaboration on scenes built using standard 3D DCC tools by applying the concept of collaborative versions to a
Lorenz Ammon, Hanspeter Bieri
openaire   +1 more source

Objects layout graph for 3D complex scenes

IEEE International Conference on Image Processing 2005, 2005
This paper shows how to extract information about the parts and their layout in a complex scene when a single range image is available. In the worst case, the complexity of the scene includes: no shape-restrictions, shades, occlusion, cluttering, contact, surfaces viewed in oblique angles and without textures.
Antonio Adán, Pilar Merchán, Santiago Salamanca, Andrés S. Vázquez, Miguel Adán, Carlos Cerrada   +5 more
openaire   +1 more source

SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation

Neural Information Processing Systems
In this paper, we propose a new framework for zero-shot object navigation. Existing zero-shot object navigation methods prompt LLM with the text of spatially closed objects, which lacks enough scene context for in-depth reasoning.
Hang Yin, Xiuwei Xu, Zhenyu Wu, Jie Zhou, Jiwen Lu   +4 more
semanticscholar   +1 more source

History-Enhanced 3D Scene Graph Reasoning From RGB-D Sequences

IEEE transactions on circuits and systems for video technology (Print)
3D scene graph has emerged as a powerful high-level representation of the environment, and is considered a prerequisite for long-term autonomous robotic operations. However, building rich representations from RGB-D sequences remains a challenging problem.
Mingtao Feng, Chenbo Yan, Zijie Wu, Weisheng Dong, Yaonan Wang, A. Mian   +5 more
semanticscholar   +1 more source