{"url":"/method/sparse-convolutions","slug":"sparse-convolutions","name":"Sparse Convolutions","full_name":"Sparse Convolutions","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"Spatially-sparse convolutional neural networks","paper":"/paper/spatially-sparse-convolutional-neural","first_author":"Benjamin Graham","n_authors":1,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/spatially-sparse-convolutional-neural"},"source":{"url":"http://arxiv.org/abs/1409.6070v1","title":"Spatially-sparse convolutional neural networks","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":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":37,"archive_num_papers":37,"papers_newest_first":[{"paper":null,"title":"FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices","date":"2025-06-04","arxiv_id":"2506.04499","n_code_links":0,"syntology":null},{"paper":null,"title":"DecoratingFusion: A LiDAR-Camera Fusion Network with the Combination of Point-level and Feature-level Fusion","date":"2024-12-31","arxiv_id":"2501.00220","n_code_links":0,"syntology":null},{"paper":"/paper/gaussianad-gaussian-centric-end-to-end","title":"GaussianAD: Gaussian-Centric End-to-End Autonomous Driving","date":"2024-12-13","arxiv_id":"2412.10371","n_code_links":1,"syntology":{"ran":1,"of":8,"unverified":7,"pointer_only":8}},{"paper":"/paper/relational-contrastive-learning-and-masked","title":"Relational Contrastive Learning and Masked Image Modeling for Scene Text Recognition","date":"2024-11-18","arxiv_id":"2411.11219","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-and-scalable-point-cloud-generation","title":"Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models","date":"2024-08-12","arxiv_id":"2408.06145","n_code_links":2,"syntology":null},{"paper":null,"title":"PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression","date":"2024-07-08","arxiv_id":"2407.05677","n_code_links":0,"syntology":null},{"paper":"/paper/minkunext-point-cloud-based-large-scale-place","title":"MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutions","date":"2024-03-12","arxiv_id":"2403.07593","n_code_links":1,"syntology":null},{"paper":null,"title":"A Computationally Efficient Neural Video Compression Accelerator Based on a Sparse CNN-Transformer Hybrid Network","date":"2023-12-17","arxiv_id":"2312.10716","n_code_links":0,"syntology":null},{"paper":"/paper/xcube-mathcal-x-3-large-scale-3d-generative","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","date":"2023-12-06","arxiv_id":"2312.03806","n_code_links":1,"syntology":{"ran":5,"of":5,"unverified":0,"pointer_only":5}},{"paper":null,"title":"ResQ: Residual Quantization for Video Perception","date":"2023-08-18","arxiv_id":"2308.09511","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-fully-convolutional-geometric","title":"Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation","date":"2023-07-28","arxiv_id":"2307.15514","n_code_links":1,"syntology":null},{"paper":null,"title":"UnLoc: A Universal Localization Method for Autonomous Vehicles using LiDAR, Radar and/or Camera Input","date":"2023-07-03","arxiv_id":"2307.00741","n_code_links":0,"syntology":null},{"paper":"/paper/pvt-ssd-single-stage-3d-object-detector-with","title":"PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer","date":"2023-05-11","arxiv_id":"2305.06621","n_code_links":1,"syntology":null},{"paper":null,"title":"Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection","date":"2023-04-06","arxiv_id":"2304.02867","n_code_links":0,"syntology":null},{"paper":"/paper/insmos-instance-aware-moving-object","title":"InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data","date":"2023-03-07","arxiv_id":"2303.03909","n_code_links":1,"syntology":null},{"paper":"/paper/fastpillars-a-deployment-friendly-pillar","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","date":"2023-02-05","arxiv_id":"2302.02367","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Transferring dense object detection models to event-based data","date":"2022-10-05","arxiv_id":"2210.02607","n_code_links":0,"syntology":null},{"paper":null,"title":"CARNet:Compression Artifact Reduction for Point Cloud Attribute","date":"2022-09-17","arxiv_id":"2209.08276","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep Open-Set Recognition for Silicon Wafer Production Monitoring","date":"2022-08-30","arxiv_id":"2208.14071","n_code_links":0,"syntology":null},{"paper":null,"title":"Inter-Frame Compression for Dynamic Point Cloud Geometry Coding","date":"2022-07-25","arxiv_id":"2207.12554","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-tensor-based-point-cloud-attribute","title":"Sparse Tensor-based Point Cloud Attribute Compression","date":"2022-04-03","arxiv_id":"2204.01023","n_code_links":1,"syntology":null},{"paper":"/paper/minkloc3d-si-3d-lidar-place-recognition-with","title":"MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity","date":"2021-12-13","arxiv_id":"2112.06539","n_code_links":1,"syntology":null},{"paper":null,"title":"Deep Point Cloud Reconstruction","date":"2021-11-23","arxiv_id":"2111.11704","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-tensor-based-multiscale-representation","title":"Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression","date":"2021-11-20","arxiv_id":"2111.10633","n_code_links":2,"syntology":null},{"paper":"/paper/traffic4cast-large-scale-traffic-prediction","title":"Traffic4cast -- Large-scale Traffic Prediction using 3DResNet and Sparse-UNet","date":"2021-11-10","arxiv_id":"2111.05990","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":0}},{"paper":null,"title":"RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection","date":"2021-06-25","arxiv_id":"2106.13365","n_code_links":0,"syntology":null},{"paper":"/paper/points2sound-from-mono-to-binaural-audio","title":"Points2Sound: From mono to binaural audio using 3D point cloud scenes","date":"2021-04-26","arxiv_id":"2104.12462","n_code_links":1,"syntology":{"ran":2,"of":4,"unverified":2,"pointer_only":0}},{"paper":"/paper/sparse-auxiliary-networks-for-unified","title":"Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion","date":"2021-03-30","arxiv_id":"2103.16690","n_code_links":1,"syntology":null},{"paper":"/paper/af-2-s3net-attentive-feature-fusion-with","title":"(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network","date":"2021-02-08","arxiv_id":"2102.04530","n_code_links":0,"syntology":null},{"paper":"/paper/cross-shape-graph-convolutional-networks","title":"Cross-Shape Attention for Part Segmentation of 3D Point Clouds","date":"2020-03-20","arxiv_id":"2003.09053","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":7},{"task":"/task/object-detection-1","name":"object-detection","papers":7},{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":6},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":6},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":5},{"task":"/task/attribute","name":"Attribute","papers":4},{"task":"/task/decoder","name":"Decoder","papers":4},{"task":"/task/object","name":"Object","papers":4},{"task":"/task/3d-semantic-segmentation","name":"3D Semantic Segmentation","papers":3},{"task":"/task/segmentation","name":"Segmentation","papers":3},{"task":"/task/3d-part-segmentation","name":"3D Part Segmentation","papers":2},{"task":"/task/autonomous-navigation","name":"Autonomous Navigation","papers":2},{"task":"/task/autonomous-vehicles","name":"Autonomous Vehicles","papers":2},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":2},{"task":"/task/optical-flow-estimation","name":"Optical Flow Estimation","papers":2},{"task":"/task/point-cloud-completion","name":"Point Cloud Completion","papers":2},{"task":"/task/pose-estimation","name":"Pose Estimation","papers":2},{"task":"/task/quantization","name":"Quantization","papers":2},{"task":"/task/real-time-object-detection","name":"Real-Time Object Detection","papers":2},{"task":"/task/representation-learning","name":"Representation Learning","papers":2}],"tasks_shown":20,"n_tasks":62,"usage_by_year":[{"year":"2014","papers":1},{"year":"2015","papers":1},{"year":"2016","papers":1},{"year":"2017","papers":2},{"year":"2019","papers":2},{"year":"2020","papers":1},{"year":"2021","papers":8},{"year":"2022","papers":5},{"year":"2023","papers":9},{"year":"2024","papers":6},{"year":"2025","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/sparse-convolutions"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}