OpenSGA: Efficient 3D Scene Graph Alignment in the Open World
Autonomous Multi-Robots Lab, Department of Cognitive Robotics, School of Mechanical Engineering, Delft University of Technology, 2628 CD, Delft, Netherlands(代尔夫特理工大学机械工程学院认知机器人学系自主多机器人实验室);Mobile Robotics Lab, School of Computation, Information and Technology, Technical University of Munich(慕尼黑技术大学计算、信息与技术学院移动机器人实验室)
Gang Chen, Sebastián Barbas Laina, Stefan Leutenegger, Javier Alonso-Mora
Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations. This enables efficient scene understanding and object-level relocalization when a robot revisits a place, as well as global map fusion across multiple agents. Such capabilities are essential for robots that require long-term memory for long-horizon tasks involving interactions with the environment. Existing approaches mainly focus on subscan-to-subscan (S2S) alignment and depend heavily on geometric point-cloud features, leaving frame-to-scan (F2S) alignment and open-set vision-language features underexplored. In addition, existing datasets for scene graph alignment remain small-scale with limited object diversity, constraining systematic training and evaluation. We present a unified and efficient scene graph alignment framework that predicts object correspondences by fusing vision-language, textual, and geometric features with spatial context. The framework comprises modules such as a distance-gated spatial attention encoder, a minimum-cost-flow-based allocator, and a global scene embedding generator to achieve accurate alignment even under large coordinate discrepancies. We further introduce ScanNet-SG, a large-scale dataset generated via an automated annotation pipeline with over 700k samples, covering 509 object categories from ScanNet labels and over 3k categories from GPT-4o-based tagging. Experiments show that our method achieves the best overall performance on both F2S and S2S tasks, substantially outperforming existing scene graph alignment methods. Our code and dataset are released at: https://autonomousrobots.nl/paper_websites/opensga.
An Industrial Dataset for Scene Acquisitions and Functional Schematics Alignment
1 Universit\'e Paris-Saclay, ENS Paris-Saclay, CNRS, Centre Borelli, 91190, Gif-sur-Yvette, France 2 EDF R\&D (Electricité de France), France 3 AMIAD, Pôle Recherche, France 4 Institut Universitaire de France
Towards 3D Scene Understanding by Referring Synthetic Models
The University of Hong Kong(香港大学);The Chinese University of Hong Kong(香港中文大学);Inceptio(嬴彻科技);ShanghaiTech University(上海科技大学);Texas A&M University(得克萨斯农工大学)
GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting
Technical University of Munich(慕尼黑技术大学);Universitat Politècnica de Catalunya(巴塞罗那技术大学);Google(谷歌);Munich Center for Machine Learning(慕尼黑机器学习中心);University of Tubingen(图宾根大学);ETH Zurich(苏黎世联邦理工学院);Visualais
GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration
School of Information Science and Technology, University of Science and Technology of China(中国科学技术大学信息科学技术学院);Institute of Advanced Technology, University of Science and Technology of China(中国科学技术大学先进技术研究院);Meituan Inc(美团)
SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation
Technical University of Munich(慕尼黑技术大学);BMW Group(宝马集团);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心(MCML));Google(谷歌);VisualAIs Labs GmbH(VisualAIs实验室 GmbH)
Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学深圳分校);Peng Cheng Laboratory(鹏城实验室);Harbin Institute of Technology(哈尔滨工业大学);Harbin Institute of Technology, Suzhou Research Institute(哈尔滨工业大学苏州研究院)
Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
University of Science and Technology of China(中国科学技术大学);School of Information Science and Technology(信息科学技术学院);Deep Space Exploration Laboratory(深空探测实验室)
Cross-Modal Scene Semantic Alignment for Image Complexity Assessment
School of Computer Science Cardiff University(卡迪夫大学计算机科学学院);School of Mathematical Sciences Beihang University(北航数学科学学院);Department of Information Technology University of Klagenfurt(克雷格弗特大学信息技术系);School of Biomedical Engineering Shenzhen University(深圳大学生物医学工程学院);School of Artificial Intelligence Sun Yat-sen University(中山大学人工智能学院)
Multi-level Cross-modal Feature Alignment via Contrastive Learning towards Zero-shot Classification of Remote Sensing Image Scenes
Henan Key Laboratory of Big Data Analysis and Processing(河南省大数据分析与处理重点实验室);Henan Engineering Laboratory of Spatial Information Processing(河南省空间信息处理工程实验室);Henan Industrial Technology Academy of Spatio-Temporal Big Data, Henan University(河南大学河南时空大数据产业技术研究院)
TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts
School of Electrical Engineering, Xi’an Jiaotong University(西安交通大学电气工程学院);Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(香港理工大学电机及电子工程学系)