{"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/mortonnet-self-supervised-learning-of-local","title":"MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds","arxiv_id":"1904.00230","date":"2019-03-30","proceeding":null,"authors":["Ali Thabet","Humam Alwassel","Bernard Ghanem"],"abstract":"We present a self-supervised task on point clouds, in order to learn\nmeaningful point-wise features that encode local structure around each point.\nOur self-supervised network, named MortonNet, operates directly on\nunstructured/unordered point clouds. Using a multi-layer RNN, MortonNet\npredicts the next point in a point sequence created by a popular and fast Space\nFilling Curve, the Morton-order curve. The final RNN state (coined Morton\nfeature) is versatile and can be used in generic 3D tasks on point clouds. In\nfact, we show how Morton features can be used to significantly improve\nperformance (+3% for 2 popular semantic segmentation algorithms) in the task of\nsemantic segmentation of point clouds on the challenging and large-scale S3DIS\ndataset. We also show how MortonNet trained on S3DIS transfers well to another\nlarge-scale dataset, vKITTI, leading to an improvement over state-of-the-art of\n3.8%. Finally, we use Morton features to train a much simpler and more stable\nmodel for part segmentation in ShapeNet. Our results show how our\nself-supervised task results in features that are useful for 3D segmentation\ntasks, and generalize well to other datasets.","url_abs":"http://arxiv.org/abs/1904.00230v1","url_pdf":"http://arxiv.org/pdf/1904.00230v1.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":"mortonnet-self-supervised-learning-of-local","repo_url":"https://github.com/alitabet/morton-net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.00230","atlas_url":"https://app.syntology.ai/?focus=1904.00230","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}