{"url":"/method/votr","slug":"votr","name":"VoTr","full_name":"Voxel Transformer","full_name_withheld":false,"description_markdown":"**VoTr** is a [Transformer](https://paperswithcode.com/method/transformer)-based 3D backbone for 3D object detection from point clouds. It contains a series of sparse and submanifold voxel modules. Submanifold voxel modules perform multi-head self-attention strictly on the non-empty voxels, while sparse voxel modules can extract voxel features at empty locations. Long-range relationships between voxels are captured via self-attention.\r\n\r\nGiven the fact that non-empty voxels are naturally sparse but numerous, directly applying standard Transformer on voxels is non-trivial. To this end, VoTr uses a sparse voxel module and a submanifold voxel module, which can operate on the empty and non-empty voxel positions effectively. To further enlarge the attention range while maintaining comparable computational overhead to the convolutional counterparts, two attention mechanisms are used for [multi-head attention](https://paperswithcode.com/method/multi-head-attention) in those two modules: Local Attention and Dilated Attention. Furthermore [Fast Voxel Query](https://paperswithcode.com/method/fast-voxel-query) is used to accelerate the querying process in multi-head attention.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Voxel Transformer for 3D Object Detection","paper":"/paper/voxel-transformer-for-3d-object-detection","first_author":"Jiageng Mao","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/voxel-transformer-for-3d-object-detection"},"source":{"url":"https://arxiv.org/abs/2109.02497v2","title":"Voxel Transformer for 3D Object Detection","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 Object Detection Models","url":"/methods/category/3d-object-detection-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/voxel-transformer-for-3d-object-detection","title":"Voxel Transformer for 3D Object Detection","date":"2021-09-06","arxiv_id":"2109.02497","n_code_links":1,"syntology":{"ran":0,"of":7,"unverified":7,"pointer_only":7}}],"papers_shown":1,"tasks":[{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/object-recognition","name":"Object Recognition","papers":1},{"task":"/task/object-detection-1","name":"object-detection","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/votr"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}