![]() ![]() ![]() ![]() It adopts a unified 2D/3D anchor design and an auxiliary task to detect 2D/3D lanes simultaneously, enhancing the feature consistency and sharing the benefits of multi-task learning. Our model generates BEV features by attending to related front-view local regions with camera parameters as a reference. PersFormer is an end-to-end monocular 3D lane detector with a novel Transformer-based spatial feature transformation module. This repository is the PyTorch implementation for PersFormer. Our blog | Slides | Presentation video (4min) | Online talk (50min) | Poster.Third-party In-depth Blog on Persformer (recommended).Paper: arXiv 2203.11089, ECCV 2022 Oral Presentation (2.7% acceptance rate).Li Chen ∗†, Chonghao Sima ∗, Yang Li ∗, Zehan Zheng, Jiajie Xu, Xiangwei Geng, Hongyang Li †, Conghui He, Jianping Shi, Yu Qiao, Junchi Yan. PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark PersFormer: a New Baseline for 3D Laneline Detection ![]()
0 Comments
Leave a Reply. |