{"url":"/method/ct3d","slug":"ct3d","name":"CT3D","full_name":"CT3D","full_name_withheld":false,"description_markdown":"**CT3D** is a two-stage 3D object detection framework that leverages a high-quality region proposal network and a Channel-wise [Transformer](https://paperswithcode.com/method/transformer) architecture. The proposed CT3D simultaneously performs proposal-aware embedding and channel-wise context aggregation for the point features within each proposal. Specifically, CT3D uses a proposal's keypoints for spatial contextual modelling and learns attention propagation in the encoding module, mapping the proposal to point embeddings. Next, a new channel-wise decoding module enriches the query-key interaction via channel-wise re-weighting to effectively merge multi-level contexts, which contributes to more accurate object predictions. \r\n\r\nIn CT3D, the raw points are first fed into the [RPN](https://paperswithcode.com/method/rpn) for generating 3D proposals. Then the raw points along with the corresponding proposals are processed by the channel-wise Transformer composed of the proposal-to-point encoding module and the channel-wise decoding module. Specifically, the proposal-to-point encoding module is to modulate each point feature with global proposal-aware context information. After that, the encoded point features are transformed into an effective proposal feature representation by the\r\nchannel-wise decoding module for confidence prediction and box regression.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2108.10723v2","title":"Improving 3D Object Detection with Channel-wise Transformer","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":2,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/ct3d-improving-3d-object-detection-with","title":"CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer","date":"2024-06-12","arxiv_id":"2406.08152","n_code_links":1,"syntology":null},{"paper":"/paper/improving-3d-object-detection-with-channel","title":"Improving 3D Object Detection with Channel-wise Transformer","date":"2021-08-23","arxiv_id":"2108.10723","n_code_links":1,"syntology":{"ran":6,"of":12,"unverified":6,"pointer_only":0}}],"papers_shown":2,"tasks":[{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/region-proposal","name":"Region Proposal","papers":1}],"tasks_shown":6,"n_tasks":6,"usage_by_year":[{"year":"2021","papers":1},{"year":"2024","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/ct3d"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}