{"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/efficient-3d-semantic-segmentation-with-1","title":"Efficient 3D Semantic Segmentation with Superpoint Transformer","arxiv_id":"2306.08045","date":"2023-06-13","proceeding":"ICCV 2023 1","authors":["Damien Robert","Hugo Raguet","Loic Landrieu"],"abstract":"We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition point clouds into a hierarchical superpoint structure, which makes our preprocessing 7 times faster than existing superpoint-based approaches. Additionally, we leverage a self-attention mechanism to capture the relationships between superpoints at multiple scales, leading to state-of-the-art performance on three challenging benchmark datasets: S3DIS (76.0% mIoU 6-fold validation), KITTI-360 (63.5% on Val), and DALES (79.6%). With only 212k parameters, our approach is up to 200 times more compact than other state-of-the-art models while maintaining similar performance. Furthermore, our model can be trained on a single GPU in 3 hours for a fold of the S3DIS dataset, which is 7x to 70x fewer GPU-hours than the best-performing methods. Our code and models are accessible at github.com/drprojects/superpoint_transformer.","url_abs":"https://arxiv.org/abs/2306.08045v2","url_pdf":"https://arxiv.org/pdf/2306.08045v2.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":"efficient-3d-semantic-segmentation-with-1","repo_url":"https://github.com/drprojects/superpoint_transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-dales","task":"3D Semantic Segmentation","dataset":"DALES","model":"Superpoint Transformer","rank_in_archive_order":2,"of":9,"metrics":{"Model size":"212K","Overall Accuracy":"97.5","mIoU":"79.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-kitti-360","task":"3D Semantic Segmentation","dataset":"KITTI-360","model":"Superpoint Transformer","rank_in_archive_order":7,"of":8,"metrics":{"Model size":"777K","miou Val":"63.5"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-s3dis","task":"3D Semantic Segmentation","dataset":"S3DIS","model":"Superpoint Transformer","rank_in_archive_order":5,"of":6,"metrics":{"mAcc":"85.8","mIoU (6-Fold)":"76.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"Superpoint Transformer","rank_in_archive_order":10,"of":54,"metrics":{"Mean IoU":"76.0","Number of params":"0.212M","Params (M)":"0.212","mAcc":"85.8","mIoU":"76.0","oAcc":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"Superpoint Transformer","rank_in_archive_order":35,"of":61,"metrics":{"Number of params":"212K","mAcc":"77.3","mIoU":"68.9","oAcc":"89.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.08045","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}