{"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-and-visualizing-localized-geometric","title":"Learning and Visualizing Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes","arxiv_id":"1711.04851","date":"2017-11-13","proceeding":null,"authors":["Sambit Ghadai","Aditya Balu","Adarsh Krishnamurthy","Soumik Sarkar"],"abstract":"3D Convolutional Neural Networks (3D-CNN) have been used for object\nrecognition based on the voxelized shape of an object. However, interpreting\nthe decision making process of these 3D-CNNs is still an infeasible task. In\nthis paper, we present a unique 3D-CNN based Gradient-weighted Class Activation\nMapping method (3D-GradCAM) for visual explanations of the distinct local\ngeometric features of interest within an object. To enable efficient learning\nof 3D geometries, we augment the voxel data with surface normals of the object\nboundary. We then train a 3D-CNN with this augmented data and identify the\nlocal features critical for decision-making using 3D GradCAM. An application of\nthis feature identification framework is to recognize difficult-to-manufacture\ndrilled hole features in a complex CAD geometry. The framework can be extended\nto identify difficult-to-manufacture features at multiple spatial scales\nleading to a real-time design for manufacturability decision support system.","url_abs":"http://arxiv.org/abs/1711.04851v3","url_pdf":"http://arxiv.org/pdf/1711.04851v3.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-and-visualizing-localized-geometric","repo_url":"https://github.com/idealab-isu/GPView","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-recognition","task_name":"3D Object Recognition"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}