{"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/a-unified-point-based-framework-for-3d","title":"A Unified Point-Based Framework for 3D Segmentation","arxiv_id":"1908.00478","date":"2019-08-01","proceeding":null,"authors":["Hung-Yueh Chiang","Yen-Liang Lin","Yueh-Cheng Liu","Winston H. Hsu"],"abstract":"3D point cloud segmentation remains challenging for structureless and textureless regions. We present a new unified point-based framework for 3D point cloud segmentation that effectively optimizes pixel-level features, geometrical structures and global context priors of an entire scene. By back-projecting 2D image features into 3D coordinates, our network learns 2D textural appearance and 3D structural features in a unified framework. In addition, we investigate a global context prior to obtain a better prediction. We evaluate our framework on ScanNet online benchmark and show that our method outperforms several state-of-the-art approaches. We explore synthesizing camera poses in 3D reconstructed scenes for achieving higher performance. In-depth analysis on feature combinations and synthetic camera pose verify that features from different modalities benefit each other and dense camera pose sampling further improves the segmentation results.","url_abs":"https://arxiv.org/abs/1908.00478v4","url_pdf":"https://arxiv.org/pdf/1908.00478v4.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":"a-unified-point-based-framework-for-3d","repo_url":"https://github.com/ken012git/joint_point_based","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.00478","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}