用几何约束替代学习位置编码，提升车载视觉的鸟瞰图语义分割性能。
Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation
- 引入视点极线约束构建注意力场，替代传统位置编码。
- 在地图语义分割上达到2%的mIoU提升，精度显著更高。
- 无需学习相机配置，通用性更强，适合实际自动驾驶场景。
自动驾驶车辆需要准确理解周围环境的语义信息以做出安全决策。近年来，纯视觉方法受到广泛关注，特别是通过多摄像头图像生成鸟瞰图（BEV）的方法在空间理解任务中表现优异。本文针对基于Transformer的方法依赖学习的位置编码来关联图像与BEV特征的问题，提出利用极线几何约束构建“极线注意力场”（Epipolar Attention Fields），将其作为注意力机制中的新属性项，替代传统的学习型位置编码。实验表明，所提方法EAFormer在地图语义分割任务上相比先前方法提升2% mIoU，且在相机配置未知的情况下展现出更优的泛化能力。
原文摘要 · Abstract (English)
Spatial understanding of the semantics of the surroundings is a key capability needed by autonomous cars to enable safe driving decisions. Recently, purely vision-based solutions have gained increasing research interest. In particular, approaches extracting a bird's eye view (BEV) from multiple cameras have demonstrated great performance for spatial understanding. This paper addresses the dependency on learned positional encodings to correlate image and BEV feature map elements for transformer-based methods. We propose leveraging epipolar geometric constraints to model the relationship between cameras and the BEV by Epipolar Attention Fields. They are incorporated into the attention mechanism as a novel attribution term, serving as an alternative to learned positional encodings. Experiments show that our method EAFormer outperforms previous BEV approaches by 2% mIoU for map semantic segmentation and exhibits superior generalization capabilities compared to implicitly learning the camera configuration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。