{"url":"/method/deltaconv","slug":"deltaconv","name":"DeltaConv","full_name":"DeltaConv","full_name_withheld":false,"description_markdown":"Anisotropic convolution is a central building block of CNNs but challenging to transfer to surfaces. DeltaConv learns combinations and compositions of operators from vector calculus, which are a natural fit for curved surfaces. The result is a simple and robust anisotropic convolution operator for point clouds with state-of-the-art results.","description_state":"present","introduced_year":null,"introduced_by":{"title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","paper":"/paper/deltaconv-anisotropic-point-cloud-learning","first_author":"Ruben Wiersma","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deltaconv-anisotropic-point-cloud-learning"},"source":{"url":"https://arxiv.org/abs/2111.08799v5","title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"3D Representations","url":"/methods/category/3d-representations","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/deltaconv-anisotropic-point-cloud-learning","title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","date":"2021-11-16","arxiv_id":"2111.08799","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/3d-part-segmentation","name":"3D Part Segmentation","papers":1},{"task":"/task/3d-point-cloud-classification","name":"3D Point Cloud Classification","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/point-cloud-classification","name":"Point Cloud Classification","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1}],"tasks_shown":6,"n_tasks":6,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/deltaconv"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}