论文标题
pandepth：联合全盘细分和深度完成
PanDepth: Joint Panoptic Segmentation and Depth Completion
论文作者
论文摘要
在涉及多个计算机视觉任务的自动驾驶应用程序中，以语义了解3D环境是关键的。多任务模型为给定场景提供了不同类型的输出，在保持计算成本较低的同时产生了更全面的表示。我们提出了一个多任务模型，用于使用RGB图像和稀疏深度图完成综合分割和深度完成。我们的模型成功地预测了完全致密的深度图，并为每个输入框架执行语义分割，实例分割和全盘分段。在Virtual Kitti 2数据集上进行了广泛的实验，我们证明了我们的模型可以解决多个任务，而没有显着增加计算成本，同时保持高准确性的性能。代码可从https://github.com/juanb09111/pandepth.git获得
Understanding 3D environments semantically is pivotal in autonomous driving applications where multiple computer vision tasks are involved. Multi-task models provide different types of outputs for a given scene, yielding a more holistic representation while keeping the computational cost low. We propose a multi-task model for panoptic segmentation and depth completion using RGB images and sparse depth maps. Our model successfully predicts fully dense depth maps and performs semantic segmentation, instance segmentation, and panoptic segmentation for every input frame. Extensive experiments were done on the Virtual KITTI 2 dataset and we demonstrate that our model solves multiple tasks, without a significant increase in computational cost, while keeping high accuracy performance. Code is available at https://github.com/juanb09111/PanDepth.git
