{"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/let-images-give-you-more-point-cloud-cross","title":"Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis","arxiv_id":"2210.04208","date":"2022-10-09","proceeding":null,"authors":["Xu Yan","Heshen Zhan","Chaoda Zheng","Jiantao Gao","Ruimao Zhang","Shuguang Cui","Zhen Li"],"abstract":"Although recent point cloud analysis achieves impressive progress, the paradigm of representation learning from a single modality gradually meets its bottleneck. In this work, we take a step towards more discriminative 3D point cloud representation by fully taking advantages of images which inherently contain richer appearance information, e.g., texture, color, and shade. Specifically, this paper introduces a simple but effective point cloud cross-modality training (PointCMT) strategy, which utilizes view-images, i.e., rendered or projected 2D images of the 3D object, to boost point cloud analysis. In practice, to effectively acquire auxiliary knowledge from view images, we develop a teacher-student framework and formulate the cross modal learning as a knowledge distillation problem. PointCMT eliminates the distribution discrepancy between different modalities through novel feature and classifier enhancement criteria and avoids potential negative transfer effectively. Note that PointCMT effectively improves the point-only representation without architecture modification. Sufficient experiments verify significant gains on various datasets using appealing backbones, i.e., equipped with PointCMT, PointNet++ and PointMLP achieve state-of-the-art performance on two benchmarks, i.e., 94.4% and 86.7% accuracy on ModelNet40 and ScanObjectNN, respectively. Code will be made available at https://github.com/ZhanHeshen/PointCMT.","url_abs":"https://arxiv.org/abs/2210.04208v1","url_pdf":"https://arxiv.org/pdf/2210.04208v1.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":"let-images-give-you-more-point-cloud-cross","repo_url":"https://github.com/zhanheshen/pointcmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"let-images-give-you-more-point-cloud-cross","repo_url":"https://github.com/yanx27/2dpass","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"PointNet2+PointCMT","rank_in_archive_order":14,"of":111,"metrics":{"Mean Accuracy":"91.2","Number of params":"1.62M","Overall Accuracy":"94.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"PointCMT","rank_in_archive_order":46,"of":77,"metrics":{"Mean Accuracy":"84.8","Number of params":"12.6M","Overall Accuracy":"86.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.04208","atlas_url":"https://app.syntology.ai/?focus=2210.04208","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}