{"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/sparse-pointpillars-exploiting-sparsity-in","title":"Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems","arxiv_id":"2106.06882","date":"2021-06-12","proceeding":null,"authors":["Kyle Vedder","Eric Eaton"],"abstract":"Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D object detector that maintains and exploits this input sparsity to decrease runtimes over non-sparse baselines and avoids the tradeoff between pseudoimage area and runtime. We present results on KITTI, a canonical 3D detection dataset, and Matterport-Chair, a novel Matterport3D-derived chair detection dataset from scenes in real furnished homes. We evaluate runtime characteristics using a desktop GPU, an embedded ML accelerator, and a robot CPU, demonstrating that our method results in significant detection speedups (2X or more) for embedded systems with only a modest decrease in detection quality. Our work represents a new approach for practitioners to optimize models for embedded systems by maintaining and exploiting input sparsity throughout their entire pipeline to reduce runtime and resource usage while preserving detection performance.","url_abs":"https://arxiv.org/abs/2106.06882v3","url_pdf":"https://arxiv.org/pdf/2106.06882v3.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":"sparse-pointpillars-exploiting-sparsity-in","repo_url":"https://github.com/kylevedder/SparsePointPillars","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"sparse-pointpillars-exploiting-sparsity-in","repo_url":"https://github.com/Mind23-2/MindCode-5/tree/main/pointpillars","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"sparse-pointpillars-exploiting-sparsity-in","repo_url":"https://github.com/code-implementation1/Code6/tree/main/pointpillars","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"birds-eye-view-object-detection","task_name":"Birds Eye View Object Detection"},{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"object-detection","task_name":"Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.06882","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}