In this work, we present WidthFormer, a novel transformer-based Bird's-Eye-View (BEV) 3D detection method tailored for real-time autonomous-driving applications. WidthFormer is computationally efficient, robust and does not require any special engineering effort to deploy. In this work, we propose a novel 3D positional encoding mechanism capable of accurately encapsulating 3D geometric information, which enables our model to generate high-quality BEV representations with only a single transformer decoder layer. This mechanism is also beneficial for existing sparse 3D object detectors. Inspired by the recently-proposed works, we further improve our model's efficiency by vertically compressing the image features when serving as attention keys and values. We also introduce two modules to compensate for potential information loss due to feature compression. Experimental evaluation on the widely-used nuScenes 3D object detection benchmark demonstrates that our method outperforms previous approaches across different 3D detection architectures. More importantly, our model is highly efficient. For example, when using $256\times 704$ input images, it achieves 1.5 ms and 2.8 ms latency on NVIDIA 3090 GPU and Horizon Journey-5 edge computing chips, respectively. Furthermore, WidthFormer also exhibits strong robustness to different degrees of camera perturbations. Our study offers valuable insights into the deployment of BEV transformation methods in real-world, complex road environments. Code is available at https://github.com/ChenhongyiYang/WidthFormer .

翻译：本文提出WidthFormer，一种专为实时自动驾驶应用设计的新型基于Transformer的鸟瞰视角（BEV）三维检测方法。WidthFormer计算高效、鲁棒性强，且无需特殊工程投入即可部署。本文提出一种新型三维位置编码机制，能够精确封装三维几何信息，使模型仅需单个Transformer解码器层即可生成高质量BEV表征。该机制同样有益于现有稀疏三维目标检测器。受近期研究工作启发，我们通过将图像特征在作为注意力键和值时进行垂直压缩，进一步提升模型效率。同时引入两个模块以补偿特征压缩可能造成的信息损失。在广泛使用的nuScenes三维目标检测基准上的实验评估表明，本方法在不同三维检测架构中均优于先前方法。更重要的是，本模型具有极高效率：例如，使用$256\times 704$输入图像时，在NVIDIA 3090 GPU和地平线Journey-5边缘计算芯片上分别实现1.5毫秒和2.8毫秒延迟。此外，WidthFormer对不同程度的相机扰动展现出强鲁棒性。本研究为BEV变换方法在实际复杂道路环境中的部署提供了重要见解。代码已开源至https://github.com/ChenhongyiYang/WidthFormer。