{"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/pointmixer-mlp-mixer-for-point-cloud","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","arxiv_id":"2111.11187","date":"2021-11-22","proceeding":null,"authors":["Jaesung Choe","Chunghyun Park","Francois Rameau","Jaesik Park","In So Kweon"],"abstract":"MLP-Mixer has newly appeared as a new challenger against the realm of CNNs and transformer. Despite its simplicity compared to transformer, the concept of channel-mixing MLPs and token-mixing MLPs achieves noticeable performance in visual recognition tasks. Unlike images, point clouds are inherently sparse, unordered and irregular, which limits the direct use of MLP-Mixer for point cloud understanding. In this paper, we propose PointMixer, a universal point set operator that facilitates information sharing among unstructured 3D points. By simply replacing token-mixing MLPs with a softmax function, PointMixer can \"mix\" features within/between point sets. By doing so, PointMixer can be broadly used in the network as inter-set mixing, intra-set mixing, and pyramid mixing. Extensive experiments show the competitive or superior performance of PointMixer in semantic segmentation, classification, and point reconstruction against transformer-based methods.","url_abs":"https://arxiv.org/abs/2111.11187v5","url_pdf":"https://arxiv.org/pdf/2111.11187v5.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":"pointmixer-mlp-mixer-for-point-cloud","repo_url":"https://github.com/lifebeyondexpectations/eccv22-pointmixer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pointmixer-mlp-mixer-for-point-cloud","repo_url":"https://github.com/LifeBeyondExpectations/PointMixer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pointmixer-mlp-mixer-for-point-cloud","repo_url":"https://github.com/hrisi/tree-species-classification","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":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"point-cloud-reconstruction","task_name":"Point cloud reconstruction"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"mlp-mixer","method_name":"MLP-Mixer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"PointMixer","rank_in_archive_order":52,"of":111,"metrics":{"Mean Accuracy":"91.4","Number of params":"6.5M","Overall Accuracy":"93.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"PointMixer","rank_in_archive_order":27,"of":61,"metrics":{"Number of params":"6.5M","mAcc":"77.4","mIoU":"71.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.11187","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}