OpenSGA: Efficient 3D Scene Graph Alignment in the Open World

• URL: http://arxiv.org/abs/2605.10484v1
• Date: Mon, 11 May 2026 12:44:18 GMT
• Title: OpenSGA: Efficient 3D Scene Graph Alignment in the Open World
• Abstract summary: Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations.<n>Existing approaches mainly focus on subscan-to-subscan (S2S) alignment and depend heavily on geometric point-cloud features.<n>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.
• Score: 27.9502908270849
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SG2Loc: Sequential Visual Localization on 3D Scene Graphs [108.42363585468458]
  This paper introduces a novel, lightweight approach to sequential visual localization using 3D scene graphs.<n>By leveraging a compact scene graph and efficient semantic matching, our method significantly reduces storage while maintaining performance on real-world datasets.
  arXiv  Detail & Related papers  (2026-06-10T10:03:21Z)
• Hierarchical Object Representation for Spatial Robot Perception: Points, Meshes, and Superquadrics [7.735876865294663]
  Hierarchical 3D Scene Graphs (3DSG) have emerged as an actionable and scalable representation for long-term autonomy.<n>We introduce a hierarchical object representation that can be leveraged for high-fidelity object-level reconstruction.<n>We show that our superquadric-based map alignment method outperforms the current state-of-the-art object based map alignment method ROMAN.
  arXiv  Detail & Related papers  (2026-06-01T01:45:47Z)
• Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces [116.57196064763924]
  We extend the benchmark coverage by introducing dense tabletop objects and explicit multi-level functional relationships.<n>This work introduces critical challenges involving small-scale, dense, and similar instances.<n>We propose an open-vocabulary pipeline based on 2D visual grounding and 3D graph optimization.
  arXiv  Detail & Related papers  (2026-05-15T09:14:50Z)
• Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation [21.553363236403822]
  3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding.<n>Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.<n>We propose a graph-guided data augmentation framework with dual-level constraints for realistic 3D scene synthesis.
  arXiv  Detail & Related papers  (2025-07-30T13:25:36Z)
• Open-Vocabulary Octree-Graph for 3D Scene Understanding [54.11828083068082]
  Octree-Graph is a novel scene representation for open-vocabulary 3D scene understanding. An adaptive-octree structure is developed that stores semantics and depicts the occupancy of an object adjustably according to its shape.
  arXiv  Detail & Related papers  (2024-11-25T10:14:10Z)
• WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments [33.25040383298019]
  $WildScenes$ is a bi-modal benchmark dataset consisting of high-resolution 2D images and dense 3D LiDAR point clouds. The data is trajectory-centric with accurate localization and globally aligned point clouds. Our 3D semantic labels are obtained via an efficient, automated process that transfers the human-annotated 2D labels from multiple views into 3D point cloud sequences.
  arXiv  Detail & Related papers  (2023-12-23T22:27:40Z)
• CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion [83.30168660888913]
  We present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model.
  arXiv  Detail & Related papers  (2023-05-25T17:39:13Z)
• SGAligner : 3D Scene Alignment with Scene Graphs [84.01002998166145]
  Building 3D scene graphs has emerged as a topic in scene representation for several embodied AI applications. We focus on the fundamental problem of aligning pairs of 3D scene graphs whose overlap can range from zero to partial. We propose SGAligner, the first method for aligning pairs of 3D scene graphs that is robust to in-the-wild scenarios.
  arXiv  Detail & Related papers  (2023-04-28T14:39:22Z)
• Location-Free Scene Graph Generation [45.366540803729386]
  Scene Graph Generation (SGG) is a visual understanding task, aiming to describe a scene as a graph of entities and their relationships with each other.<n>Existing works rely on location labels in form of bounding boxes or segmentation masks, increasing annotation costs and limiting dataset expansion.<n>We break this dependency and introduce location-free scene graph generation (LF-SGG)<n>This new task aims at predicting instances of entities, as well as their relationships, without the explicit calculation of their spatial localization.
  arXiv  Detail & Related papers  (2023-03-20T08:57:45Z)
• Scan2Part: Fine-grained and Hierarchical Part-level Understanding of Real-World 3D Scans [68.98085986594411]
  We propose Scan2Part, a method to segment individual parts of objects in real-world, noisy indoor RGB-D scans. We use a sparse U-Net-based architecture that captures the fine-scale detail of the underlying 3D scan geometry. As output, we are able to predict fine-grained per-object part labels, even when the geometry is coarse or partially missing.
  arXiv  Detail & Related papers  (2022-06-06T05:43:10Z)
• Fully Convolutional Scene Graph Generation [30.194961716870186]
  This paper presents a fully convolutional scene graph generation (FCSGG) model that detects objects and relations simultaneously. FCSGG encodes objects as bounding box center points, and relationships as 2D vector fields which are named as Relation Affinity Fields (RAFs) FCSGG achieves highly competitive results on recall and zero-shot recall with significantly reduced inference time.
  arXiv  Detail & Related papers  (2021-03-30T05:25:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.