{"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/curveformer-3d-lane-detection-by-curve","title":"CurveFormer: 3D Lane Detection by Curve Propagation with Curve Queries and Attention","arxiv_id":"2209.07989","date":"2022-09-16","proceeding":null,"authors":["Yifeng Bai","Zhirong Chen","Zhangjie Fu","Lang Peng","Pengpeng Liang","Erkang Cheng"],"abstract":"3D lane detection is an integral part of autonomous driving systems. Previous CNN and Transformer-based methods usually first generate a bird's-eye-view (BEV) feature map from the front view image, and then use a sub-network with BEV feature map as input to predict 3D lanes. Such approaches require an explicit view transformation between BEV and front view, which itself is still a challenging problem. In this paper, we propose CurveFormer, a single-stage Transformer-based method that directly calculates 3D lane parameters and can circumvent the difficult view transformation step. Specifically, we formulate 3D lane detection as a curve propagation problem by using curve queries. A 3D lane query is represented by a dynamic and ordered anchor point set. In this way, queries with curve representation in Transformer decoder iteratively refine the 3D lane detection results. Moreover, a curve cross-attention module is introduced to compute the similarities between curve queries and image features. Additionally, a context sampling module that can capture more relative image features of a curve query is provided to further boost the 3D lane detection performance. We evaluate our method for 3D lane detection on both synthetic and real-world datasets, and the experimental results show that our method achieves promising performance compared with the state-of-the-art approaches. The effectiveness of each component is validated via ablation studies as well.","url_abs":"https://arxiv.org/abs/2209.07989v2","url_pdf":"https://arxiv.org/pdf/2209.07989v2.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":[],"tasks":[{"task_slug":"3d-lane-detection","task_name":"3D Lane Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"lane-detection","task_name":"Lane Detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-lane-detection-on-apollo-synthetic-3d-lane","task":"3D Lane Detection","dataset":"Apollo Synthetic 3D Lane","model":"CurveFormer","rank_in_archive_order":3,"of":10,"metrics":{"F1":"95.8","X error far":"0.326","X error near":"0.078","Z error far":"0.219","Z error near":"0.018"},"uses_additional_data":false},{"leaderboard":"/sota/3d-lane-detection-on-openlane","task":"3D Lane Detection","dataset":"OpenLane","model":"CurveFormer","rank_in_archive_order":19,"of":21,"metrics":{"Curve":"56.6","Extreme Weather":"49.7","F1 (all)":"50.5","FPS (pytorch)":"-","Intersection":"42.9","Merge & Split":"45.4","Night":"49.1","Up & Down":"45.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.07989","atlas_url":"https://app.syntology.ai/?focus=2209.07989","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}