DualCross：面向单目BEV感知的跨模态跨域自适应
DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception
AI总结：
本文提出DualCross框架，通过跨模态跨域自适应将LiDAR点云知识迁移到单目BEV感知模型，首次系统分析野外单目3D任务的跨域跨传感器适应问题，并在大规模数据集上取得最优结果。
摘要：
缩小训练与部署之间的域差距以及融合多种传感器模态，是自动驾驶中两个具有挑战性但又至关重要的课题。现有工作仅关注上述课题之一，忽视了现实场景中普遍存在的同时发生的域偏移和模态偏移。例如，一个利用在欧洲采集的多传感器数据训练得到的模型，可能需要在亚洲运行，并且只能使用部分输入传感器。在本工作中，我们提出了DualCross，一个跨模态跨域自适应框架，以促进学习更鲁棒的单目鸟瞰图（BEV）感知模型，该框架在训练阶段将一个域中LiDAR传感器的点云知识迁移到另一个域中仅使用相机的测试场景。本工作首次对野外单目3D任务中的跨域跨传感器感知与自适应进行了开放分析。我们在大规模数据集上、在广泛的域偏移条件下对我们的方法进行了基准测试，并展示了相对于各种基线的最先进结果。
英文摘要：
Closing the domain gap between training and deployment and incorporating multiple sensor modalities are two challenging yet critical topics for self-driving. Existing work only focuses on single one of the above topics, overlooking the simultaneous domain and modality shift which pervasively exists in real-world scenarios. A model trained with multi-sensor data collected in Europe may need to run in Asia with a subset of input sensors available. In this work, we propose DualCross, a cross-modality cross-domain adaptation framework to facilitate the learning of a more robust monocular bird's-eye-view (BEV) perception model, which transfers the point cloud knowledge from a LiDAR sensor in one domain during the training phase to the camera-only testing scenario in a different domain. This work results in the first open analysis of cross-domain cross-sensor perception and adaptation for monocular 3D tasks in the wild. We benchmark our approach on large-scale datasets under a wide range of domain shifts and show state-of-the-art results against various baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
