{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/scenegraphfusion-incremental-3d-scene-graph","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","arxiv_id":"2103.14898","date":"2021-03-27","proceeding":"CVPR 2021 1","authors":["Shun-Cheng Wu","Johanna Wald","Keisuke Tateno","Nassir Navab","Federico Tombari"],"abstract":"Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks. This work proposes a method to incrementally build up semantic scene graphs from a 3D environment given a sequence of RGB-D frames. To this end, we aggregate PointNet features from primitive scene components by means of a graph neural network. We also propose a novel attention mechanism well suited for partial and missing graph data present in such an incremental reconstruction scenario. Although our proposed method is designed to run on submaps of the scene, we show it also transfers to entire 3D scenes. Experiments show that our approach outperforms 3D scene graph prediction methods by a large margin and its accuracy is on par with other 3D semantic and panoptic segmentation methods while running at 35 Hz.","url_abs":"https://arxiv.org/abs/2103.14898v3","url_pdf":"https://arxiv.org/pdf/2103.14898v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"scenegraphfusion-incremental-3d-scene-graph","repo_url":"https://github.com/ShunChengWu/3DSSG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"scenegraphfusion-incremental-3d-scene-graph","repo_url":"https://github.com/ShunChengWu/SceneGraphFusion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"3d-object-classification","task_name":"3D Object Classification"},{"task_slug":"3d-scene-graph-generation","task_name":"3d scene graph generation"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"predicate-classification","task_name":"Predicate Classification"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-classification-on-3r-scan-1","task":"3D Object Classification","dataset":"3R-Scan","model":"SceneGraphFusion","rank_in_archive_order":1,"of":2,"metrics":{"Top-10 Accuracy":"0.8","Top-5 Accuracy":"0.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-classification-on-3r-scan-1","task":"3D Object Classification","dataset":"3R-Scan","model":"3DSSG [Wald2020_3dssg]","rank_in_archive_order":2,"of":2,"metrics":{"Top-10 Accuracy":"0.78","Top-5 Accuracy":"0.68"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-scannet","task":"Panoptic Segmentation","dataset":"ScanNet","model":"SceneGraphFusion","rank_in_archive_order":4,"of":4,"metrics":{"PQ":"31.5","PQ_st":"43.4","PQ_th":"30.2"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-scannetv2","task":"Panoptic Segmentation","dataset":"ScanNetV2","model":"SceneGraphFusion (NN mapping)","rank_in_archive_order":5,"of":5,"metrics":{"PQ":"31.5","Params (M)":"2.9","RQ":"42.2","SQ":"72.9"},"uses_additional_data":false},{"leaderboard":"/sota/scene-graph-generation-on-3r-scan-1","task":"Scene Graph Generation","dataset":"3R-Scan","model":"SceneGraphFusion","rank_in_archive_order":1,"of":2,"metrics":{"Top-5 Accuracy":"0.87"},"uses_additional_data":false},{"leaderboard":"/sota/scene-graph-generation-on-3r-scan-1","task":"Scene Graph Generation","dataset":"3R-Scan","model":"3DSSG [Wald2020_3dssg]","rank_in_archive_order":2,"of":2,"metrics":{"Top-5 Accuracy":"0.66"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.14898","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}