{"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/learning-3d-shapes-as-multi-layered-height","title":"Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks","arxiv_id":"1807.08485","date":"2018-07-23","proceeding":"ECCV 2018 9","authors":["Kripasindhu Sarkar","Basavaraj Hampiholi","Kiran varanasi","Didier Stricker"],"abstract":"We present a novel global representation of 3D shapes, suitable for the\napplication of 2D CNNs. We represent 3D shapes as multi-layered height-maps\n(MLH) where at each grid location, we store multiple instances of height maps,\nthereby representing 3D shape detail that is hidden behind several layers of\nocclusion. We provide a novel view merging method for combining view dependent\ninformation (Eg. MLH descriptors) from multiple views. Because of the ability\nof using 2D CNNs, our method is highly memory efficient in terms of input\nresolution compared to the voxel based input. Together with MLH descriptors and\nour multi view merging, we achieve the state-of-the-art result in\nclassification on ModelNet dataset.","url_abs":"http://arxiv.org/abs/1807.08485v2","url_pdf":"http://arxiv.org/pdf/1807.08485v2.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":"learning-3d-shapes-as-multi-layered-height","repo_url":"https://github.com/krips89/mlh_mvcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-object-classification","task_name":"3D Object Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.08485","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}