# DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception Source: [DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:53:13.696Z Authors: Yunze Man, Liang-Yan Gui, Yu-Xiong Wang Published: 2023-05-05T17:58:45.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [BEV Semantic Segmentation on nuScenes Boston -\> Singapore 1.0 (test val)](): BEV Semantic Segmentation; nuScenes Boston -\> Singapore 1.0 (test val); Drivable Area Score: 43.8. - [BEV Semantic Segmentation on nuScenes Singapore -\> Boston 1.0 (test val)](): BEV Semantic Segmentation; nuScenes Singapore -\> Boston 1.0 (test val); mIoU (Drivable Area): 45.7. - [BEV Semantic Segmentation on nuScenes Day -\> Night 1.0 (test val)](): BEV Semantic Segmentation; nuScenes Day -\> Night 1.0 (test val); Driver: 49.4. - [BEV Semantic Segmentation on nuScenes Dry -\> Rain 1.0 (test val)](): BEV Semantic Segmentation; nuScenes Dry -\> Rain 1.0 (test val); Class IoU: Driveable Area: 67.9. ## Original sources and implementation [Original paper]() [PDF]()