{"url":"/method/submanifold-convolutions","slug":"submanifold-convolutions","name":"Submanifold Convolution","full_name":"Submanifold Convolution","full_name_withheld":false,"description_markdown":"**Submanifold Convolution (SC)** is a spatially sparse [convolution](https://paperswithcode.com/method/convolution) operation used for tasks with sparse data like semantic segmentation of 3D point clouds. An SC convolution computes the set of active sites in the same way as a regular convolution: it looks for the presence of any active sites in its receptive field of size $f^{d}$. If the input has size $l$ then the output will have size $\\left(l − f + s\\right)/s$. Unlike a regular convolution, an SC convolution discards the ground state for non-active sites by assuming that the input from those sites is zero. For more details see the [paper](https://paperswithcode.com/paper/3d-semantic-segmentation-with-submanifold), or the official code [here](https://github.com/facebookresearch/SparseConvNet).","description_state":"present","introduced_year":null,"introduced_by":{"title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","paper":"/paper/3d-semantic-segmentation-with-submanifold","first_author":"Benjamin Graham","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/3d-semantic-segmentation-with-submanifold"},"source":{"url":"http://arxiv.org/abs/1711.10275v1","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/facebookresearch/SparseConvNet/blob/159e5f9a2349c776c422dce9f5b4493519303dc2/sparseconvnet/submanifoldConvolution.py#L14","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":7,"papers_newest_first":[{"paper":"/paper/self-supervised-enhancement-for-depth-from-a","title":"Self-Supervised Enhancement for Depth from a Lightweight ToF Sensor with Monocular Images","date":"2025-06-16","arxiv_id":"2506.13444","n_code_links":2,"syntology":null},{"paper":null,"title":"UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection","date":"2025-03-15","arxiv_id":"2503.12009","n_code_links":0,"syntology":null},{"paper":null,"title":"Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection","date":"2024-08-25","arxiv_id":"2408.13798","n_code_links":0,"syntology":null},{"paper":"/paper/pointgroup-dual-set-point-grouping-for-3d","title":"PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation","date":"2020-04-03","arxiv_id":"2004.01658","n_code_links":4,"syntology":{"ran":0,"of":5,"unverified":5,"pointer_only":0}},{"paper":"/paper/occuseg-occupancy-aware-3d-instance","title":"OccuSeg: Occupancy-aware 3D Instance Segmentation","date":"2020-03-14","arxiv_id":"2003.06537","n_code_links":0,"syntology":null},{"paper":"/paper/4d-spatio-temporal-convnets-minkowski","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","date":"2019-04-18","arxiv_id":"1904.08755","n_code_links":8,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":2}},{"paper":"/paper/3d-semantic-segmentation-with-submanifold","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","date":"2017-11-28","arxiv_id":"1711.10275","n_code_links":6,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":3}}],"papers_shown":7,"tasks":[{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":4},{"task":"/task/3d-instance-segmentation-1","name":"3D Instance Segmentation","papers":2},{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":2},{"task":"/task/3d-semantic-segmentation","name":"3D Semantic Segmentation","papers":2},{"task":"/task/clustering","name":"Clustering","papers":2},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/4d-spatio-temporal-semantic-segmentation","name":"4D Spatio Temporal Semantic Segmentation","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/lidar-semantic-segmentation","name":"LIDAR Semantic Segmentation","papers":1},{"task":"/task/mamba","name":"Mamba","papers":1},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":1},{"task":"/task/panoptic-segmentation","name":"Panoptic Segmentation","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/robust-3d-semantic-segmentation","name":"Robust 3D Semantic Segmentation","papers":1},{"task":"/task/scene-understanding","name":"Scene Understanding","papers":1},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":1}],"tasks_shown":20,"n_tasks":21,"usage_by_year":[{"year":"2017","papers":1},{"year":"2019","papers":1},{"year":"2020","papers":2},{"year":"2024","papers":1},{"year":"2025","papers":2}],"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/submanifold-convolutions"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}